4 papers
Vision Guided Target Conditioned Control for Autonomous Excavation
Shuai Zhao, Ji-An Pan, Junwei Li +5
Autonomous excavation requires an intelligent control system that can convert spatial work intent into coordinated bucket motion under contact-rich soil interaction. This paper pre…
Multi-Source Human-in-the-Loop Digital Twin Testbed for Connected and Autonomous Vehicles in Mixed Traffic Flow
Jianghong Dong, Chunying Yang, Mengchi Cai +5
In the emerging mixed traffic environments, Connected and Autonomous Vehicles (CAVs) have to interact with surrounding human-driven vehicles (HDVs). This paper introduces MSH-MCCT…
From Optimizable to Interactable: Mixed Digital Twin-Empowered Testing of Vehicle-Infrastructure Cooperation Systems
Jianghong Dong, Chunying Yang, Mengchi Cai +4
Sufficient testing under corner cases is critical for the long-term operation of vehicle-infrastructure cooperation systems (VICS). However, existing corner-case generation methods…
Conformal Symplectic Optimization for Stable Reinforcement Learning
Yao Lyu, Xiangteng Zhang, Shengbo Eben Li +5
Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle…