Publications

recently published

Shuijing Liu, Aamir Hasan, Kaiwen Hong, Runxuan Wang, Peixin Chang, Zachary Mizrachi, Justin Lin, D Livingston McPherson, Wendy A Rogers, and Katherine Driggs-Campbell. “A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding,” IEEE Robotics and Automation Letters (RA-L), 2024.
[arXiv] [website]

Persons with visual impairments (PwVI) have difficulties understanding and navigating spaces around them. Current wayfinding technologies either focus solely on navigation or provide limited communication about the environment. Motivated by recent advances in visual-language grounding and semantic navigation, we propose DRAGON, a guiding robot powered by a dialogue system and the ability to associate the environment with natural language. By understanding the commands from the user, DRAGON is able to guide the user to the desired landmarks on the map, describe the environment, and answer questions from visual observations. Through effective utilization of dialogue, the robot can ground the user’s free-form descriptions to landmarks in the environment, and give the user semantic information through spoken language. We conduct a user study with blindfolded participants in an everyday indoor environment. Our results demonstrate that DRAGON is able to communicate with the user smoothly, provide a good guiding experience, and connect users with their surrounding environment in an intuitive manner.

see full abstract
show less

Zhe Huang, Hongyu Chen, and Katherine Driggs-Campbell. “Neural Informed RRT* with Point-based Network Guidance for Optimal Sampling-based Path Planning,” IEEE International Conference on Robotics and Automation (ICRA), 2024.
[arXiv] [code]

Sampling-based planning algorithms like Rapidly-exploring Random Tree (RRT) are versatile in solving path planning problems. RRT* offers asymptotical optimality but requires growing the tree uniformly over the free space, which leaves room for efficiency improvement. To accelerate convergence, informed approaches sample states in an ellipsoidal subset of the search space determined by current path cost during iteration. Learning-based alternatives model the topology of the search space and infer the states close to the optimal path to guide planning. We combine the strengths from both sides and propose Neural Informed RRT* with Point-based Network Guidance. We introduce Point-based Network to infer the guidance states, and integrate the network into Informed RRT* for guidance state refinement. We use Neural Connect to build connectivity of the guidance state set and further boost performance in challenging planning problems. Our method surpasses previous works in path planning benchmarks while preserving probabilistic completeness and asymptotical optimality. We demonstrate the deployment of our method on mobile robot navigation in the real world.

see full abstract
show less

Go to top

2023

Sourya Basu*, Pulkit Katdare*, Prasanna Sattigeri, Vijil Chenthamarakshan, Katherine Rose Driggs-Campbell, Payel Das, Lav R Varshney “Efficient Equivariant Transfer Learning from Pretrained Models,” Conference on Neural Information Processing Systems (NeurIPS), 2023.
[arXiv]

Efficient transfer learning algorithms are key to the success of foundation models on diverse downstream tasks even with limited data. Recent works of Basu et al. (2023) and Kaba et al. (2022) propose group averaging (equitune) and optimization-based methods, respectively, over features from group-transformed inputs to obtain equivariant outputs from non-equivariant neural networks. While Kaba et al. (2022) are only concerned with training from scratch, we find that equitune performs poorly on equivariant zero-shot tasks despite good finetuning results. We hypothesize that this is because pretrained models provide better quality features for certain transformations than others and simply averaging them is deleterious. Hence, we propose λ-equitune that averages the features using importance weights, λs. These weights are learned directly from the data using a small neural network, leading to excellent zero-shot and finetuned results that outperform equitune. Further, we prove that λ-equitune is equivariant and a universal approximator of equivariant functions. Additionally, we show that the method of Kaba et al. (2022) used with appropriate loss functions, which we call equizero, also gives excellent zero-shot and finetuned performance. Both equitune and equizero are special cases of λ- equitune. To show the simplicity and generality of our method, we validate on a wide range of diverse applications and models such as 1) image classification using CLIP, 2) deep Q-learning, 3) fairness in natural language generation (NLG), 4) compositional generalization in languages, and 5) image classification using pretrained CNNs such as Resnet and Alexnet.

see full abstract
show less

Haonan Chen, Yilong Niu, Kaiwen Hong, Shuijing Liu, Yixuan Wang, Yunzhu Li, and Katherine Driggs-Campbell “Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks,” Conference on Robot Learning (CoRL), 2023.
Best Paper Award Finalist.
[arXiv]

Stowing, the task of placing objects in cluttered shelves or bins, is a common task in warehouse and manufacturing operations. However, this task is still predominantly carried out by human workers as stowing is challenging to automate due to the complex multi-object interactions and long-horizon nature of the task. Previous works typically involve extensive data collection and costly human labeling of semantic priors across diverse object categories. This paper presents a method to learn a generalizable robot stowing policy from predictive model of object interactions and a single demonstration with behavior primitives. We propose a novel framework that utilizes Graph Neural Networks (GNNs) to predict object interactions within the parameter space of behavioral primitives. We further employ primitive-augmented trajectory optimization to search the parameters of a predefined library of heterogeneous behavioral primitives to instantiate the control action. Our framework enables robots to proficiently execute long-horizon stowing tasks with a few keyframes (3-4) from a single demonstration. Despite being solely trained in a simulation, our framework demonstrates remarkable generalization capabilities. It efficiently adapts to a broad spectrum of real-world conditions, including various shelf widths, fluctuating quantities of objects, and objects with diverse attributes such as sizes and shapes.

see full abstract
show less

Peixin Chang, Shuijing Liu, Tianchen Ji, Neeloy Chakraborty, Kaiwen Hong, and Katherine Driggs-Campbell “A Data-Efficient Visual-Audio Representation with Intuitive Fine-tuning for Voice-Controlled Robots,” Conference on Robot Learning (CoRL), 2023.
[pdf]

A command-following robot that serves people in everyday life must continually improve itself in deployment domains with minimal help from its end users, instead of engineers. Previous methods are either difficult to continuously improve after the deployment or require a large number of new labels during fine-tuning. Motivated by (self-)supervised contrastive learning, we propose a novel representation that generates an intrinsic reward function for command-following robot tasks by associating images with sound commands. After the robot is deployed in a new domain, the representation can be updated intuitively and data-efficiently by non-experts without any hand-crafted reward functions. We demonstrate our approach on various sound types and robotic tasks, including navigation and manipulation with raw sensor inputs. In simulated and real-world experiments, we show that our system can continually self-improve in previously unseen scenarios given fewer new labeled data, while still achieving better performance over previous methods.

see full abstract
show less

Pulkit Katdare, Nan Jiang, and Katherine Driggs-Campbell. “Marginalized Importance Sampling for Off-Environment Policy Evaluation,” Conference on Robot Learning (CoRL), 2023.
[arXiv]

Reinforcement Learning (RL) methods are typically sample-inefficient, making it challenging to train and deploy RL-policies in real world robots. Even a robust policy trained in simulation requires a real-world deployment to assess their performance. This paper proposes a new approach to evaluate the real-world performance of agent policies prior to deploying them in the real world. Our approach incorporates a simulator along with real-world offline data to evaluate the performance of any policy using the framework of Marginalized Importance Sampling (MIS). Existing MIS methods face two challenges:(1) large density ratios that deviate from a reasonable range and (2) indirect supervision, where the ratio needs to be inferred indirectly, thus exacerbating estimation error. Our approach addresses these challenges by introducing the target policy’s occupancy in the simulator as an intermediate variable and learning the density ratio as the product of two terms that can be learned separately. The first term is learned with direct supervision and the second term has a small magnitude, thus making it computationally efficient. We analyze the sample complexity as well as error propagation of our two step-procedure. Furthermore, we empirically evaluate our approach on Sim2Sim environments such as Cartpole, Reacher, and Half-Cheetah. Our results show that our method generalizes well across a variety of Sim2Sim gap, target policies and offline data collection policies. We also demonstrate the performance of our algorithm on a Sim2Real task of validating the performance of a 7 DoF robotic arm using offline data along with the Gazebo simulator.

see full abstract
show less

Yu-Chen Chang, Nitish Gandi, Kazuki Shin, Ye-Ji Mun, Katherine Driggs-Campbell, and Joohyung Kim. “Specifying Target Objects in Robot Teleoperation Using Speech and Natural Eye Gaze,” IEEE International Conference on Humanoid Robots (Humanoids), 2023.

Current approaches in robot teleoperation often require significant mental and physical effort. In this study, we propose a new intent detection framework to teleoperate robotic arms based on human speech and natural eye gaze. Our framework applies instance segmentation on the robot’s camera image and predicts the human’s intended object through matching eye-gaze data, instance masks, instance classes, and transcribed words. Our experiment results show a prediction accuracy between 90.7% and 98.6%, including cases when the target objects are duplicated or occluded. The prediction accuracy of the combination of eye gaze and speech inputs outperformed the prediction accuracy of eye gaze input only, between 79.9% and 89.2%, and speech input only, between 25.3% and 71.6%. Moreover, we observe that eye gaze input has a greater importance than speech input in improving prediction accuracy when two duplicated target objects are present in the scene. Our results from NASA TLX questionnaires show that teleoperating the robotic arms with our proposed framework requires little effort including cases when the target objects are duplicated or occluded.

see full abstract
show less

Aamir Hasan, Neeloy Chakraborty, Haonan Chen, Jung-Hoon Cho, Cathy Wu, and Katherine Driggs-Campbell. “PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems,” IEEE Intelligent Transportation Systems Conference (ITSC), 2023.
[arXiv] [website] [code]

Intelligent driving systems can be used to mitigate congestion through simple actions, thus improving many socioeconomic factors such as commute time and gas costs. However, these systems assume precise control over autonomous vehicle fleets, and are hence limited in practice as they fail to account for uncertainty in human behavior. Piecewise Constant (PC) Policies address these issues by structurally modeling the likeness of human driving to reduce traffic congestion in dense scenarios to provide action advice to be followed by human drivers. However, PC policies assume that all drivers behave similarly. To this end, we develop a co-operative advisory system based on PC policies with a novel driver trait conditioned Personalized Residual Policy, PeRP. PeRP advises drivers to behave in ways that mitigate traffic congestion. We first infer the driver’s intrinsic traits on how they follow instructions in an unsupervised manner with a variational autoencoder. Then, a policy conditioned on the inferred trait adapts the action of the PC policy to provide the driver with a personalized recommendation. Our system is trained in simulation with novel driver modeling of instruction adherence. We show that our approach successfully mitigates congestion while adapting to different driver behaviors, with 4 to 22% improvement in average speed over baselines.

see full abstract
show less

Andre Schreiber, Tianchen Ji, D Livingston McPherson, and Katherine Driggs-Campbell. “An Attentional Recurrent Neural Network for Occlusion-Aware Proactive Anomaly Detection in Field Robot Navigation,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
[arXiv] [code]

The use of mobile robots in unstructured environments like the agricultural field is becoming increasingly common. The ability for such field robots to proactively identify and avoid failures is thus crucial for ensuring efficiency and avoiding damage. However, the cluttered field environment introduces various sources of noise (such as sensor occlusions) that make proactive anomaly detection difficult. Existing approaches can show poor performance in sensor occlusion scenarios as they typically do not explicitly model occlusions and only leverage current sensory inputs. In this work, we present an attention-based recurrent neural network architecture for proactive anomaly detection that fuses current sensory inputs and planned control actions with a latent representation of prior robot state. We enhance our model with an explicitly-learned model of sensor occlusion that is used to modulate the use of our latent representation of prior robot state. Our method shows improved anomaly detection performance and enables mobile field robots to display increased resilience to predicting false positives regarding navigation failure during periods of sensor occlusion, particularly in cases where all sensors are briefly occluded.

see full abstract
show less

W.J. Wagner, A. Soylemezoglu, D. Nottage, K. Driggs-Campbell. “Online Soil Property Estimation for Autonomous Earthmoving Using Physics-Infused Neural Networks,” Conference of the International Society for Terrain-Vehicle Systems (ISTVS), 2023.
[arXiv]

A novel, learning-based method for online estimation of soil properties using a physics-infused neural network is presented. The network is trained to produce estimates of soil cohesion, angle of internal friction, soil-tool friction, soil failure angle, and residual depth of cut which are then passed through an earthmoving model based on the fundamental equation of earthmoving (FEE) to produce an estimated force. The network ingests a short history kinematic observations along with past control commands and predicts interaction forces to near 10% of the machine limits . To validate the approach, an earthmoving simulation of a bladed vehicle is developed using Vortex Studio, enabling comparison of the estimated parameters to pseudo-ground-truth values, which is nearly impossible in real world experiments. The proposed approach is shown to enable accurate estimation of interaction forces and produces meaningful parameter estimates even when the model and the environmental physics deviate substantially.

see full abstract
show less

Yixuan Wang*, Yunzhu Li*, Katherine Driggs-Campbell, Fei-Fei Li, and Jiajun Wu. “Dynamic-Resolution Model Learning for Object Pile Manipulation,” Robotics: Science and Systems (RSS), 2023.
[arXiv]

Dynamics models learned from visual observations have shown to be effective in various robotic manipulation tasks. One of the key questions for learning such dynamics models is what scene representation to use. Prior works typically assume representation at a fixed dimension or resolution, which may be inefficient for simple tasks and ineffective for more complicated tasks. In this work, we investigate how to learn dynamic and adaptive representations at different levels of abstraction to achieve the optimal trade-off between efficiency and effectiveness. Specifically, we construct dynamic-resolution particle representations of the environment and learn a unified dynamics model using graph neural networks (GNNs) that allows continuous selection of the abstraction level. During test time, the agent can adaptively determine the optimal resolution at each model-predictive control (MPC) step. We evaluate our method in object pile manipulation, a task we commonly encounter in cooking, agriculture, manufacturing, and pharmaceutical applications. Through comprehensive evaluations both in the simulation and the real world, we show that our method achieves significantly better performance than state-of-the-art fixed-resolution baselines at the gathering, sorting, and redistribution of granular object piles made with various instances like coffee beans, almonds, corn, etc.

see full abstract
show less

Ye-Ji Mun, Masha Itkina, Shuijing Liu, and Katherine Driggs-Campbell. “Occlusion-Aware Crowd Navigation Using People as Sensors,” IEEE International Conference on Robotics and Automation (ICRA), 2023.
[arXiv] [youtube] [code]

Autonomous navigation in crowded spaces poses a challenge for mobile robots due to the highly dynamic, partially observable environment. Occlusions are highly prevalent in such settings due to a limited sensor field of view and obstructing human agents. Previous work has shown that observed interactive behaviors of human agents can be used to estimate potential obstacles despite occlusions. We propose integrating such social inference techniques into the planning pipeline. We use a variational autoencoder with a specially designed loss function to learn representations that are meaningful for occlusion inference. This work adopts a deep reinforcement learning approach to incorporate the learned representation for occlusion-aware planning. In simulation, our occlusion-aware policy achieves comparable collision avoidance performance to fully observable navigation by estimating agents in occluded spaces. We demonstrate successful policy transfer from simulation to the real-world Turtlebot 2i. To the best of our knowledge, this work is the first to use social occlusion inference for crowd navigation.

see full abstract
show less

Shahab Sagheb, Ye-Ji Mun, Neema Ahmadian, Benjamin Christie, Andrea Bajcsy, Katherine Driggs-Campbell, and Dylan Losey. “Towards Robots that Influence Humans over Long-Term Interaction,” IEEE International Conference on Robotics and Automation (ICRA), 2023.
[arXiv] [youtube]

When humans interact with robots influence is inevitable. Consider an autonomous car driving near a human: the speed and steering of the autonomous car will affect how the human drives. Prior works have developed frameworks that enable robots to influence humans towards desired behaviors. But while these approaches are effective in the short-term (i.e., the first few human-robot interactions), here we explore long-term influence (i.e., repeated interactions between the same human and robot). Our central insight is that humans are dynamic: people adapt to robots, and behaviors which are influential now may fall short once the human learns to anticipate the robot’s actions. With this insight, we experimentally demonstrate that a prevalent game-theoretic formalism for generating influential robot behaviors becomes less effective over repeated interactions. Next, we propose three modifications to Stackelberg games that make the robot’s policy both influential and unpredictable. We finally test these modifications across simulations and user studies: our results suggest that robots which purposely make their actions harder to anticipate are better able to maintain influence over long-term interaction.

see full abstract
show less

Zhe Huang*, Ye-Ji Mun*, Xiang Li, Yixing Xie, Ninghan Zhong, Weihang Liang, Junyi Geng, Tan Chen, and Katherine Driggs-Campbell. “Hierarchical Intention Tracking for Robust Human-Robot Collaboration in Industrial Assembly Tasks,” IEEE International Conference on Robotics and Automation (ICRA), 2023.
[arXiv]

Collaborative robots require effective human intention estimation to safely and smoothly work with humans in less structured tasks such as industrial assembly, where human intention continuously changes. We propose the concept of intention tracking and introduce a collaborative robot system that concurrently tracks intentions at hierarchical levels. The high-level intention is tracked to estimate human’s interaction pattern and enable robot to (1) avoid collision with human to minimize interruption and (2) assist human to correct failure. The low-level intention estimate provides robot with task-related information. We implement the system on a UR5e robot and demonstrate robust, seamless and ergonomic human-robot collaboration in an ablative pilot study of an assembly use case.

see full abstract
show less

Shuijing Liu, Peixin Chang, Zhe Huang, Neeloy Chakraborty, Kaiwen Hong, Weihang Liang, D. Livingston McPherson, Junyi Geng, and Katherine Driggs-Campbell. “Socially-Aware Robot Crowd Navigation with Attention-Based Interaction Graph,” IEEE International Conference on Robotics and Automation (ICRA), 2023.
[arXiv] [website] [code]

We study the problem of safe and intention-aware robot navigation in dense and interactive crowds. Most previous reinforcement learning (RL) based methods fail to consider different types of interactions among all agents or ignore the intentions of people, which results in performance degradation. To learn a safe and efficient robot policy, we propose a novel recurrent graph neural network with attention mechanisms to capture heterogeneous interactions among agents through space and time. To encourage longsighted robot behaviors, we infer the intentions of dynamic agents by predicting their future trajectories for several timesteps. The predictions are incorporated into a model-free RL framework to prevent the robot from intruding into the intended paths of other agents. We demonstrate that our method enables the robot to achieve good navigation performance and non-invasiveness in challenging crowd navigation scenarios. We successfully transfer the policy learned in simulation to a real-world TurtleBot 2i.

see full abstract
show less

Neeloy Chakraborty, Aamir Hasan, Shuijing Liu, Tianchen Ji, Weihang Liang, D. Livingston McPherson, and Katherine Driggs-Campbell. “Structural Attention-based Recurrent Variational Autoencoder for Highway Vehicle Anomaly Detection,” ACM International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
[arXiv] [website] [code]

In autonomous driving, detection of abnormal driving behaviors is essential to ensure the safety of vehicle controllers. Prior works in vehicle anomaly detection have shown that modeling interactions between agents improves detection accuracy, but certain abnormal behaviors where structured road information is paramount are poorly identified, such as wrong-way and off-road driving. We propose a novel unsupervised framework for highway anomaly detection named Structural Attention-Based Recurrent VAE (SABeR-VAE), which explicitly uses the structure of the environment to aid anomaly identification. Specifically, we use a vehicle self-attention module to learn the relations among vehicles on a road, and a separate lane-vehicle attention module to model the importance of permissible lanes to aid in trajectory prediction. Conditioned on the attention modules’ outputs, a recurrent encoder-decoder architecture with a stochastic Koopman operator-propagated latent space predicts the next states of vehicles. Our model is trained end-to-end to minimize prediction loss on normal vehicle behaviors, and is deployed to detect anomalies in (ab)normal scenarios. By combining the heterogeneous vehicle and lane information, SABeR-VAE and its deterministic variant, SABeR-AE, improve abnormal AUPR by 18% and 25% respectively on the simulated MAAD highway dataset over STGAE-KDE. Furthermore, we show that the learned Koopman operator in SABeR-VAE enforces interpretable structure in the variational latent space. The results of our method indeed show that modeling environmental factors is essential to detecting a diverse set of anomalies in deployment.

see full abstract
show less

Peixin Chang, Shuijing Liu, and Katherine Driggs-Campbell. “Learning Visual-Audio Representations for Voice-Controlled Robots,” IEEE International Conference on Robotics and Automation (ICRA), 2023.
[arXiv]

Inspired by sensorimotor theory, we propose a novel pipeline for voice-controlled robots. Previous work relies on explicit labels of sounds and images as well as extrinsic reward functions. Not only do such approaches have little resemblance to human sensorimotor development, but also require hand-tuning rewards and extensive human labor. To address these problems, we learn a representation that associates images and sound commands with minimal supervision. Using this representation, we generate an intrinsic reward function to learn robotic tasks with reinforcement learning. We demonstrate our approach on three robot platforms, a TurtleBot3, a Kuka-IIWA arm, and a Kinova Gen3 robot, which hear a command word, identify the associated target object, and perform precise control to approach the target. We show that our method outperforms previous work across various sound types and robotic tasks empirically. We successfully deploy the policy learned in simulator to a real-world Kinova Gen3.

see full abstract
show less

Go to top

2022

Yuan Shen, Shanduojiao Jiang, Yanlin Chen, Eileen Yang, Xilun Jin, Yuliang Fan, and Katherine Driggs-Campbell. “To Explain or Not to Explain: A Study on the Necessity of Explanations in Autonomous Driving,” NeurIPS Workshop on Progress and Challenges in Building Trustworthy Embodied AI (TEA), 2022.
[arXiv] Best Paper Award Winner.

Explainable AI, in the context of autonomous systems, like self-driving cars, has drawn broad interests from researchers. Recent studies have found that providing explanations for autonomous vehicles’ actions has many benefits (e.g., increased trust and acceptance), but put little emphasis on when an explanation is needed and how the content of explanation changes with driving context. In this work, we investigate which scenarios people need explanations and how the critical degree of explanation shifts with situations and driver types. Through a user experiment, we ask participants to evaluate how necessary an explanation is and measure the impact on their trust in self-driving cars in different contexts. Moreover, we present a self-driving explanation dataset with first-person explanations and associated measures of the necessity for 1103 video clips, augmenting the Berkeley Deep Drive Attention dataset. Our research reveals that driver types and driving scenarios dictate whether an explanation is necessary. In particular, people tend to agree on the necessity for near-crash events but hold different opinions on ordinary or anomalous driving situations.

see full abstract
show less

Tianchen Ji, Junyi Geng, and Katherine Driggs-Campbell. “Robust Model Predictive Control with State Estimation under Set-Membership Uncertainty,” CDC 2022.
[arXiv]

Robust design of autonomous systems under uncertainty is an important and challenging problem. In practice, state disturbances and state estimation error may cause a controller to fail to accomplish its task or even to stabilize the system. In this paper, we propose a novel tube-based robust model predictive control design based on set-membership state estimation for constrained systems with unknown but bounded state and output disturbances. With more accurate and efficient error bounding methods, the proposed controller ensures robust constraint satisfaction, guarantees recursive feasibility and stability, generates less conservative behavior than the previous work, and scales well to high-dimensional robotic applications. Our simulated experiments on three different systems (double integrator, robotic walker, and quadrotor) demonstrate that the proposed controller is robust against a larger range of disturbances and results in superior closed-loop performance than baseline methods.

see full abstract
show less

W. Jacob Wagner*, Katherine Driggs-Campbell, and Ahmet Soylemezoglu. “Model Learning and Predictive Control for Autonomous Obstacle Reduction via Bulldozing,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.

see full abstract
show less

Peter Du, Katherine Driggs-Campbell, and Roy Dong. “Improving the Feasibility of Moment-Based Safety Analysis for Stochastic Dynamics,” To appear in Transactions on Automatic Control (TAC), 2022.
[arXiv]

Given a stochastic dynamical system modelled via stochastic differential equations (SDEs), we evaluate the safety of the system through characterizations of its exit time moments. We lift the (possibly nonlinear) dynamics into the space of the occupation and exit measures to obtain a set of linear evolution equations which depend on the infinitesimal generator of the SDE. Coupled with appropriate semidefinite positive matrix constraints, this yields a moment-based approach for the computation of exit time moments of SDEs with polynomial drift and diffusion dynamics. However, the existing moment approach suffers from drawbacks which impede its applicability to the analysis of higher dimensional physical systems. To apply the existing approach, the dynamics of the systems are limited to polynomials of the state – excluding a large majority of real world examples. Computational scalability is also poor as the dimensionality of the state increases, largely due to the combinatorial growth of the optimization program. In this paper, we propose changes to the existing moment method to make feasible the safety analysis of higher dimensional physical systems. The restriction to polynomial dynamics is lifted by using a state augmentation method which allows one to generate the evolution equations for a broader class of nonlinear stochastic systems. We then reformulate the constraints of the optimization to mitigate the computational limitations associated with an increase in state dimensionality. We employ our methodology on two example processes to characterize their safety via expected exit times and demonstrate the ability to handle multi-dimensional physical systems that were previously unsupported by the existing SDP method of moments.

see full abstract
show less

Yuan Shen, Niviru Wijayaratne, Pranav Sriram, Aamir Hasan, Peter Du, and Katherine Driggs-Campbell. “CoCAtt: A Cognitive-Conditioned Driver Attention Dataset,” IEEE Intelligent Transportation Systems Conference (ITSC), 2022.
[arXiv]

The task of driver attention prediction has drawn considerable interest among researchers in robotics and the autonomous vehicle industry. Driver attention prediction can play an instrumental role in mitigating and preventing high-risk events, like collisions and casualties. However, existing driver attention prediction models neglect the distraction state and intention of the driver, which can significantly influence how they observe their surroundings. To address these issues, we present a new driver attention dataset, CoCAtt (Cognitive-Conditioned Attention). Unlike previous driver attention datasets, CoCAtt includes per-frame annotations that describe the distraction state and intention of the driver. In addition, the attention data in our dataset is captured in both manual and autopilot modes using eye-tracking devices of different resolutions. Our results demonstrate that incorporating the above two driver states into attention modeling can improve the performance of driver attention prediction. To the best of our knowledge, this work is the first to provide autopilot attention data. Furthermore, CoCAtt is currently the largest and the most diverse driver attention dataset in terms of autonomy levels, eye tracker resolutions, and driving scenarios.

see full abstract
show less

Haonan Chen, Tianchen Ji, Shuijing Liu, and Katherine Driggs-Campbell. “Combining Model-Based Controllers and Generative Adversarial Imitation Learning for Traffic Simulation,” IEEE Intelligent Transportation Systems Conference (ITSC), 2022.

An accurate model of human drivers is essential to validate the performance of autonomous vehicles in multiagent and interactive scenarios. Previous works on human driver modeling either use model-based controllers that are not adaptive and need laborious parameter-tuning or learn an end-to-end black box model that has few safety guarantees. We propose a two-stage hybrid driver model, where a high-level neural network generates driver traits that are used as the parameters of the low-level model-based controllers for simulated drivers. Compared with end-to-end methods, our model is safer due to the safety guarantees of the low-level controllers. Meanwhile, the output parameters of our model have interpretable meanings that allows us to better understand the behaviors of drivers. We train our model using generative adversarial imitation learning with reward augmentation and parameter sharing from real-world vehicle trajectory data. By combining data-driven and model-based approaches, our method simulates traffic agents with expressive, safe, and human-like behaviors. We demonstrate that our method outperforms state-of-the-art baselines in terms of imitation performance and safety in a multi-agent highway driving scenario.

see full abstract
show less

Megan A. Bayles, Travis Kadylak, Shuijing Liu, Aamir Hasan, Weihang Liang, Kaiwen Hong, Kathrine Driggs-Campbell, and Wendy A. Rogers. “An Interdisciplinary Approach: Potential for Robotic Support to Address Wayfinding Barriers Among Persons with Visual Impairments,” Human Factors and Ergonomics Society’s International Annual Meeting (HFES), 2022.

Persons with Vision Impairments (PwVI) often have difficulties navigating through indoor environments and their challenges and solution strategies can change based on their level of familiarity with the different locations. A collaborative effort was made to design a user needs assessment to understand the collaborative nature of human-robot interaction for wayfinding. The user study was an interview study to discuss with PwVI their navigation experience in familiar, somewhat familiar, and unfamiliar locations. Following this, we also discussed their current solution strategies for wayfinding in those locations to discuss how they could imagine a robot to support wayfinding. We report on four case studies to discuss findings identified specific user needs, such as vocal direction and orientation to learn a new environment and navigate, and highlighted common strategies, such as supplemental lighting, different types of human assistance, and technologies used (i.e. white canes).

see full abstract
show less

Abhi Kamboj, Tianchen Ji, and Katherine Driggs-Campbell. “Examining Audio Communication Mechanisms for Supervising Fleets of Agricultural Robots,” IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2022.

Agriculture is facing a labor crisis, leading to increased interest in fleets of small, under-canopy robots (agbots) that can perform precise, targeted actions (e.g., crop scouting, weeding, fertilization), while being supervised by human operators remotely. However, farmers are not necessarily experts in robotics technology and will not adopt technologies that add to their workload or do not provide an immediate payoff. In this work, we explore methods for communication between a remote human operator and multiple agbots and examine the impact of audio communication on the operator’s preferences and productivity. We develop a simulation platform where agbots are deployed across a field, randomly encounter failures, and call for help from the operator. As the agbots report errors, various audio communication mechanisms are tested to convey which robot failed and what type of failure occurs. The human is tasked with verbally diagnosing the failure while completing a secondary task. A user study was conducted to test three audio communication methods: earcons, single-phrase commands, and full sentence communication. Each participant completed a survey to determine their preferences and each method’s overall effectiveness. Our results suggest that the system using short phrases is the most positively perceived by participants and may allow for the human to complete the secondary task more efficiently.

see full abstract
show less

Tianchen Ji, Roy Dong, and Katherine Driggs-Campbell. “Traversing Supervisor Problem: An Approximately Optimal Approach to Multi-Robot Assistance,” Robotics: Science and Systems (RSS), 2022.
[arXiv]

The number of multi-robot systems deployed in field applications has increased dramatically over the years. Despite the recent advancement of navigation algorithms, autonomous robots often encounter challenging situations where the control policy fails and the human assistance is required to resume robot tasks. Human-robot collaboration can help achieve high-levels of autonomy, but monitoring and managing multiple robots at once by a single human supervisor remains a challenging problem. Our goal is to help a supervisor decide which robots to assist in which order such that the team performance can be maximized. We formulate the one-to-many supervision problem in uncertain environments as a dynamic graph traversal problem. An approximation algorithm based on the profitable tour problem on a static graph is developed to solve the original problem, and the approximation error is bounded and analyzed. Our case study on a simulated autonomous farm demonstrates superior team performance than baseline methods in task completion time and human working time, and that our method can be deployed in real-time for robot fleets with moderate size.

see full abstract
show less

Aamir Hasan, Neeloy Chakraborty, Cathy Wu, and Katherine Driggs-Campbell. “Towards Co-operative Congestion Mitigation,” ICRA Workshop on Shared Autonomy in Physical Human-Robot Interaction: Adaptability and Trust, 2022.

The effects of traffic congestion are widespread and are an impedance to everyday life. Piecewise constant driving policies have shown promise in helping mitigate traffic congestion in simulation environments. However, no works currently test these policies in situations involving real human users. Thus, we propose to evaluate these policies through the use of a shared control framework in a collaborative experiment with the human driver and the driving policy aiming to co-operatively mitigate congestion. We intend to use the CARLA simulator alongside the Flow framework to conduct user studies to evaluate the affect of piecewise constant driving policies. As such, we present our in-progress work in building our framework and discuss our proposed plan on evaluating this framework through a human-in-the-loop simulation user study.

see full abstract
show less

Tan Chen, Zhe Huang, James Motes, Junyi Geng, Quang Minh Ta, Holly Dinkel, Hameed Abdul-Rashid, Jessica Myers, Ye-Ji Mun, Wei-che Lin, Yuan-yung Huang, Sizhe Liu, Marco Morales, Nancy M. Amato, Katherine Driggs-Campbell, Timothy Bretl. “Industrial Collaborative Assembly Project: Lessons in Research and Collaboration,” Spotlight presentation at ICRA 2022 Workshop on Collaborative Robots and the Work of the Future, 2022.

Significant progress in robotics reveals new opportunities to advance manufacturing. Next-generation industrial automation will require both integration of distinct robotic technologies and their application to challenging industrial environments. This paper presents lessons from a collaborative assembly project between three academic research groups and an industry partner. The goal of the project is to develop a flexible, safe, and productive manufacturing cell for sub-centimeter precision assembly. Solving this problem in a high-mix, low-volume production line motivates multiple research thrusts in robotics. This work identifies new directions in collaborative robotics for industrial applications and offers insight toward strengthening collaborations between institutions in academia and industry on the development of new technologies.

see full abstract
show less

Shuijing Liu*, Aamir Hasan*, Kaiwen Hong, Chun-Kai Yao, Justin Lin, Weihang Liang, Megan A. Bayles, Wendy A. Rogers, and Katherine Driggs-Campbell. “Designing a Wayfinding Robot for People with Visual Impairments,” ICRA Workshop on Intelligent Control Methods and Machine Learning Algorithms for Human-Robot Interaction and Assistive Robotics, 2022.

People with visual impairments (PwVI) often have difficulties navigating through unfamiliar indoor environments.
However, current wayfinding tools are fairly limited. In this short paper, we present our in-progress work on a wayfinding robot for PwVI. The robot takes an audio command from the user that specifies the intended destination. Then, the robot autonomously plans a path to navigate to the goal. We use sensors to estimate the real-time position of the user, which is fed to the planner to improve the safety and comfort of the user. In addition, the robot describes the surroundings to the user periodically to prevent disorientation and potential accidents. We demonstrate the feasibility of our design in a public indoor environment. Finally, we analyze the limitations of our current design, as well as our insights and future work.
A demonstration video can be found at https://youtu.be/BS9r5bkIass.

see full abstract
show less

Masha Itkina, Ye-Ji Mun, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “Multi-Agent Variational Occlusion Inference Using People as Sensors,” In IEEE International Conference on Robotics and Automation (ICRA), 2022.
[arXiv] [github]

Autonomous vehicles must reason about spatial occlusions in urban environments to ensure safety without being overly cautious. Prior work explored occlusion inference from observed social behaviors of road agents, hence treating people as sensors. Inferring occupancy from agent behaviors is an inherently multimodal problem; a driver may behave similarly for different occupancy patterns ahead of them (e.g., a driver may move at constant speed in traffic or on an open road). Past work, however, does not account for this multimodality, thus neglecting to model this source of aleatoric uncertainty in the relationship between driver behaviors and their environment. We propose an occlusion inference method that characterizes observed behaviors of human agents as sensor measurements, and fuses them with those from a standard sensor suite. To capture the aleatoric uncertainty, we train a conditional variational autoencoder with a discrete latent space to learn a multimodal mapping from observed driver trajectories to an occupancy grid representation of the view ahead of the driver. Our method handles multi-agent scenarios, combining measurements from multiple observed drivers using evidential theory to solve the sensor fusion problem. Our approach is validated on a real-world dataset, outperforming baselines and demonstrating real-time capable performance.

see full abstract
show less

Aamir Hasan, Pranav Sriram, and Katherine Driggs-Campbell. “Meta-path Analysis on Spatio-Temporal Graphs for Pedestrian Trajectory Prediction,” In IEEE International Conference on Robotics and Automation (ICRA), 2022.

Spatio-temporal graphs (ST-graphs) have been used to model time series tasks such as traffic forecasting, human motion modeling, and action recognition. The high-level structure and corresponding features from ST-graphs have led to improved performance over traditional architectures. However, current methods tend to be limited by simple features, despite the rich information provided by the full graph structure, which leads to inefficiencies and suboptimal performance in downstream tasks. We propose the use of features derived from meta-paths, walks across different types of edges, in ST-graphs to improve the performance of Structural Recurrent Neural Network. In this paper, we present the Meta-path Enhanced Structural Recurrent Neural Network (MESRNN), a generic framework that can be applied to any spatio-temporal task in a simple and scalable manner. We employ MESRNN for pedestrian trajectory prediction, utilizing these meta-path based features to capture the relationships between the trajectories of pedestrians at different points in time and space. We compare our MESRNN against state-of-the-art ST-graph methods on standard datasets to show the performance boost provided by meta-path information. The proposed model consistently outperforms the baselines in trajectory prediction over long time horizons by over 32%, and produces more socially compliant trajectories in dense crowds.

see full abstract
show less

Shuijing Liu, Peixin Chang, Haonan Chen, Neeloy Chakraborty, and Katherine Driggs-Campbell. “Learning to Navigate Intersections with Unsupervised Driver Trait Inference,” In IEEE International Conference on Robotics and Automation (ICRA), 2022.
[arXiv] [website] [youtube]

Navigation through uncontrolled intersections is one of the key challenges for autonomous vehicles. Identifying the subtle differences in hidden traits of other drivers can bring significant benefits when navigating in such environments. We propose an unsupervised method for inferring driver traits such as driving styles from observed vehicle trajectories. We use a variational autoencoder with recurrent neural networks to learn a latent representation of traits without any ground truth trait labels. Then, we use this trait representation to learn a policy for an autonomous vehicle to navigate through a T-intersection with deep reinforcement learning. Our pipeline enables the autonomous vehicle to adjust its actions when dealing with drivers of different traits to ensure safety and efficiency. Our method demonstrates promising performance and outperforms state-of-the-art baselines in the T-intersection scenario.

see full abstract
show less

Pulkit Katdare, Shuijing Liu, and Katherine Driggs-Campbell. “Off Environment Evaluation Using Convex Risk Minimization,” In IEEE International Conference on Robotics and Automation (ICRA), 2022.

Applying reinforcement learning (RL) methods on robots typically involves training a policy in simulation and deploying it on a robot in the real world. Because of the model mismatch between the real world and the simulator, RL agents deployed in this manner tend to perform suboptimally. To tackle this problem, researchers have developed robust policy learning algorithms that rely on synthetic noise disturbances. However, such methods do not guarantee performance in the target environment. We propose a convex risk minimization algorithm to estimate the model mismatch between the simulator and the target domain using trajectory data from both environments. We show that this estimator can be used along with the simulator to evaluate performance of an RL agents in the target domain, effectively bridging the gap between these two environments. We also show that the convergence rate of our estimator to be of the order of ${n^{-1/4}}$, where $n$ is the number of training samples. In simulation, we demonstrate how our method effectively approximates and evaluates performance on Gridworld, Cartpole, and Reacher environments on a range of policies. We also show that the our method is able to estimate performance of a 7 DOF robotic arm using the simulator and remotely collected data from the robot in the real world.

see full abstract
show less

Tianchen Ji, Arun Narenthiran Sivakumar, Girish Chowdhary, and Katherine Driggs-Campbell. “Proactive Anomaly Detection for Robot Navigation with Multi-Sensor Fusion,” IEEE Robotics and Automation Letters (RA-L), 2022.
To be presented at In IEEE International Conference on Robotics and Automation (ICRA), 2022.

Despite the rapid advancement of navigation algorithms, mobile robots often render anomalous behaviors that can lead to navigation failures. The ability to detect such anomalous behaviors is a key component in modern robots to achieve high-levels of autonomy. Reactive anomaly detection methods identify anomalous task executions based on the current robot state and thus lack the ability to alert the robot before an actual failure occurs. Such an alert delay is undesirable due to the potential damage to both the robot and the surrounding objects. We propose a proactive anomaly detection network (PAAD) for robot navigation in unstructured and uncertain environments. PAAD predicts the probability of future failure based on the planned motions from the predictive controller and the current observation from the perception module. Multi-sensor signals are fused effectively to provide robust anomaly detection in the presence of sensor occlusion as seen in field environments. Our experiments on agricultural robot data demonstrates superior failure identification performance than previous methods, and that our model can capture anomalous behaviors in real-time while maintaining a low false detection rate in cluttered fields.

see full abstract
show less

Go to top

2021

Zhe Huang, Ruohua Li, Kazuki Shin, and Katherine Driggs-Campbell, “Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction,” in IEEE Robotics and Automation Letters (RA-L), 2021.
To be presented at In IEEE International Conference on Robotics and Automation (ICRA), 2022.
[arXiv]

Multi-pedestrian trajectory prediction is an indispensable safety element of autonomous systems that interact with crowds in unstructured environments. Many recent efforts have developed trajectory prediction algorithms with focus on understanding social norms behind pedestrian motions. Yet we observe these works usually hold two assumptions that prevent them from being smoothly applied to robot applications: positions of all pedestrians are consistently tracked; the target agent pays attention to all pedestrians in the scene. The first assumption leads to biased interaction modeling with incomplete pedestrian data, and the second assumption introduces unnecessary disturbances and leads to the freezing robot problem. Thus, we propose Gumbel Social Transformer, in which an Edge Gumbel Selector samples a sparse interaction graph of partially observed pedestrians at each time step. A Node Transformer Encoder and a Masked LSTM encode the pedestrian features with the sampled sparse graphs to predict trajectories. We demonstrate that our model overcomes the potential problems caused by the assumptions, and our approach outperforms the related works in benchmark evaluation.

see full abstract
show less

Shuijing Liu, Peixin Chang, Weihang Liang, Neeloy Chakraborty, and Katherine Driggs-Campbell. “Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning,” In IEEE International Conference on Robotics and Automation (ICRA), 2021.
[arXiv] [github] [youtube]

Safe and efficient navigation through human crowds is an essential capability for mobile robots. Previous
work on robot crowd navigation assumes that the dynamics of all agents are known and well-defined. In addition, the performance of previous methods deteriorates in partially observable environments and environments with dense crowds. To tackle these problems, we propose decentralized structural-Recurrent Neural Network (DS-RNN), a novel network that reasons about spatial and temporal relationships for robot decision making
in crowd navigation. We train our network with model-free deep reinforcement learning without any expert supervision. We demonstrate that our model outperforms previous methods in challenging crowd navigation scenarios. We successfully transfer the policy learned in the simulator to a real-world TurtleBot 2i.

see full abstract
show less

Peter Du and Katherine Driggs-Campbell. “Adaptive Failure Search Using Critical States from Domain Experts.” In IEEE International Conference on Robotics and Automation (ICRA), 2021.
[arXiv]

Uncovering potential failure cases is a crucial step in the validation of safety critical systems such as autonomous vehicles. Failure search may be done through logging substantial vehicle miles in either simulation or real world testing. Due to the sparsity of failure events, naive random search approaches require significant amounts of vehicle operation hours to find potential system weaknesses. As a result, adaptive searching techniques have been proposed to efficiently explore and uncover failure trajectories of an autonomous policy in simulation. Adaptive Stress Testing (AST) is one such method that poses the problem of failure search as a Markov decision process and uses reinforcement learning techniques to find high probability failures. However, this formulation requires a probability model for the actions of all agents in the environment. In systems where the environment actions are discrete and dependencies among agents exist, it may be infeasible to fully characterize the distribution or find a suitable proxy. This work proposes the use of a data driven approach to learn a suitable classifier that tries to model how humans identify critical states and use this to guide failure search in AST. We show that the incorporation of critical states into the AST framework generates failure scenarios with increased safety violations in an autonomous driving policy with a discrete action space.

see full abstract
show less

Yuan Shen, Niviru Wijayaratne, Peter Du, SJ Jiang, and Katherine Driggs-Campbell. “AutoPreview: A Framework for Autopilot Behavior Understanding,” In CHI: Extended Abstracts, 2021.
[paper]

The behavior of self-driving cars may differ from people’s expectations (e.g. an autopilot may unexpectedly relinquish control). This expectation mismatch can cause potential and existing users to distrust self-driving technology and can increase the likelihood of accidents. We propose a simple but effective framework, AutoPreview, to enable consumers to preview a target autopilot’s potential actions in the real-world driving context before deployment. For a given target autopilot, we design a delegate policy that replicates the target autopilot behavior with explainable action representations, which can then be queried online for comparison and to build an accurate mental model. To demonstrate its practicality, we present a prototype of AutoPreview integrated with the CARLA simulator along with two potential use cases of the framework. We conduct a pilot study to investigate whether or not AutoPreview provides deeper understanding about autopilot behavior when experiencing a new autopilot policy for the first time. Our results suggest that the AutoPreview method helps users understand autopilot behavior in terms of driving style comprehension, deployment preference, and exact action timing prediction.

see full abstract
show less

Yuan Shen, Niviru Wijayaratne, and Katherine Driggs-Campbell. “Building Mental Models through Preview of Autopilot Behaviors,” in TRAITS Workshop at ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2021.
[arXiv]

Effective human-vehicle collaboration requires an appropriate understanding of vehicle behavior for safety and trust. Improving on our prior work by adding a future prediction module, we introduce our framework, calledAutoPreview, to enable humans to preview autopilot behaviors prior to direct interaction with the vehicle. Previewing autopilot behavior can help to ensure smooth human-vehicle collaboration during the initial exploration stage with the vehicle. To demonstrate its practicality, we conducted a case study on human-vehicle collaboration and built a prototype of our framework with the CARLA simulator. Additionally, we conducted a between-subject control experiment (n=10) to study whether our AutoPreview framework can provide a deeper under-standing of autopilot behavior compared to direct interaction. Our results suggest that the AutoPreview framework does, in fact, help users understand autopilot behavior and develop appropriate mental models.

see full abstract
show less

Kyle Brown, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior,” Technical Report, 2021.
[arXiv]

We present a review and taxonomy of 200 models from the literature on driver behavior modeling. We begin by introducing a mathematical framework for describing the dynamics of interactive multi-agent traffic. Based on the partially observable stochastic game, this framework provides a basis for discussing different driver modeling techniques. Our taxonomy is constructed around the core modeling tasks of state estimation, intention estimation, trait estimation, and motion prediction, and also discusses the auxiliary tasks of risk estimation, anomaly detection, behavior imitation and microscopic traffic simulation. Existing driver models are categorized based on the specific tasks they address and key attributes of their approach.

see full abstract
show less

Go to top

2020

Zhe Huang, Aamir Hasan, Kazuki Shin, Ruohua Li, and Katherine Driggs-Campbell. “Long-term Pedestrian Trajectory Prediction using Mutable Intention Filter and Warp LSTM,” In IEEE Robotics and Automation Letters, 2020.
[arXiv]
Tianchen Ji, Sri Theja Vuppala, Girish Chowdhary, and Katherine Driggs-Campbell. “Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments,” In Conference on Robot Learning (CoRL), 2020.
[arXiv] [website]
Peixin Chang, Shuijing Liu, Haonan Chen, and Katherine Driggs-Campbell. “Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control,” In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.
[arXiv] [website]
Peter Du, Zhe Huang, Tianchen Ji, Tianqi Liu, Ke Xu, Qichao Gao, Hussein Sibai, Katherine Driggs-Campbell, and Sayan Mitra. “Online Monitoring for Safe Pedestrian-Vehicle Interactions,” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2020.
[arXiv]
Carl-Johan Hoel, Katherine Driggs-Campbell, Krister Wolff, Leo Laine, Mykel J. Kochenderfer. “Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving.” In IEEE Transactions on Intelligent Vehicles, 2020.
[arXiv]

Go to top

2019

Peter Du and Katherine Driggs-Campbell. “Finding Diverse Failure Scenarios in Autonomous Systems Using Adaptive Stress Testing,” SAE International Journal of Connected and Automated Vehicles, December 2019.
Masha Itkina, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning.” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2019.
[arXiv]
Anthony Corso*, Peter Du*, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation.” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2019.
[arXiv]
Kunal Menda, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning.” In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.
[arXiv]
Xiaobai Ma, Katherine Driggs-Campbell, Zongzhang Zhang, and Mykel J. Kochenderfer. “Monte Carlo Tree Search for Policy Optimization.” In International Joint Conference on Artificial Intelligence (IJCAI), 2019.
[arXiv]
Michael Kelly, Chelsea Sidrane, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “HG-DAgger: Interactive Imitation Learning with Human Experts.” In IEEE International Conference on Robotics and Automation (ICRA), 2019.
[arXiv]
Raunak Bhattacharyya, Derek J. Phillips, Changliu Liu, Jayesh K. Gupta, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning.” In IEEE International Conference on Robotics and Automation (ICRA), 2019.
[arXiv]

Go to top

recently published

2023

2022

2021

2020

2019

Preprints

Tech Reports