Research

Intelligent Testing with Interpretable and High-Capacity Agents by Embedding Logical Structure in Neural Architectures

Human-centered Action recognition and Prediction

Autonomous Drifting: Demonstrating a Reciprocal Architecture for Motion Planning and Control

Planning Set-Based Trajectory Envelops in Dynamic Driving Environments for Guaranteed-Safe Guardian Autonomy

Hardware, control and perception for robust manipulation in cluttered environments

Leveraging Language for Generalizable, Composable, and Interactive Robot Learning

Learning Traffic Screenplays through 3D Object Detection and Tracking

Collaboration with CMU

Learning to interact with articulated objects

Physical and Functional Inductive Biases for Visual Representation Learning

Collaboration with MIT

Two-Hand Robotic Manipulation Skills

Model Predictive Control for Safe Limit Driving in Highly Dynamic Environments

Task-Driven Visual Perception

Supersizing Robot Learning through Hybrid Imitation

Joint Contextual Forecasting of Vehicle Behaviors, Actions, and Trajectories

A Model Guardian to Enforce and Improve Intelligent Vehicle Safety

Individual Driving Styles: Learning, Modeling, and Improving Driver Safety

Safe Feedback Interactions in Human-Autonomous Vehicle Systems

An Engagement Learning Approach to Generating Massive Labeled Datasets for Training AI Systems

Cloud-Aided Computer Vision for Autonomous Devices

Exploiting Depth and Motion Cues for Robust Semantic, Instance-level Segmentation and Tracking

Acquiring, Representing, and Transporting Manipulation Knowledge

Soft Robotics and Haptics for Shared Autonomy and Teleoperation

Dexterity and Perception Enhancement for Robots

Emergent Behaviors in Multi-Agent Human-Robot Teams

Interaction-Aware Control for Cars that Anticipate and Explain Complex Environments

Robust and Interpretable Machine Learning via Natural Language Explanations

Hands and Sensors for Robots That Can Do Dishes

Data-efficient Algorithms for Machine Learning with Provable Guarantees

Data-Driven Analysis of Multi-Modal Sensory Inputs for the Design of Smart Environments

Intelligent Wearable Robotics

Closing the Visual-Motor Loop with Deep Reinforcement Learning

A Macroscope for Fleets of Intelligent Vehicles

Dynamic Choice Models of Human Decision-Making

Rich Physical Human/Robot Interaction Skills in Versatile Real/Life Scenarios

Joint Contextual Forecasting of Vehicle Behaviors, Actions, and Trajectories

Uncertainty on Uncertainty, Robustness, and Simulation

Human-Centric Autonomous and Assistive Driving

Understanding Driver State in Laboratory and Naturalistic Environments

Human Behaviors and Interaction for In-Car Experiences