What went wrong? closing the sim-to-real gap via differentiable causal discovery

P Huang, X Zhang, Z Cao, S Liu, M Xu… - … on Robot Learning, 2023 - proceedings.mlr.press
Training control policies in simulation is more appealing than on real robots directly, as it
allows for exploring diverse states in an efficient manner. Yet, robot simulators inevitably …

SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation

B Stoler, I Navarro, J Francis, J Oh - arxiv preprint arxiv:2409.10320, 2024 - arxiv.org
Verification and validation of autonomous driving (AD) systems and components is of
increasing importance, as such technology increases in real-world prevalence. Safety …

Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding

A Lohner, F Compagno, J Francis… - 2024 IEEE …, 2024 - ieeexplore.ieee.org
Recognizing a traffic accident is an essential part of any autonomous driving or road
monitoring system. An accident can appear in a wide variety of forms, and understanding …

Co-Evolving Environments and Agents for Physical-World Deployments

P Huang - 2024 - search.proquest.com
In the past decade, Reinforcement Learning (RL) has made substantial strides across a
variety of domains, including chess, video games, robotics, and human preference …