8 papers
Stage-Transition Dense Reward Modeling for Reinforcement Learning
Yang Yang, Bingjie Chen, Zihan Wang +4
Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to…
HL-IK: A Lightweight Implementation of Human-Like Inverse Kinematics in Humanoid Arms
Bingjie Chen, Zihan Wang, Zhe Han +3
Traditional IK methods for redundant humanoid manipulators emphasize end-effector (EE) tracking, frequently producing configurations that are valid mechanically but not human-like.…
Deployable Vision-driven UAV River Navigation via Human-in-the-loop Preference Alignment
Zihan Wang, Jianwen Li, Li-Fan Wu +1
Rivers are critical corridors for environmental monitoring and disaster response, where Unmanned Aerial Vehicles (UAVs) guided by vision-driven policies can provide fast, low-cost…
Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics Model
Zihan Wang, Nina Mahmoudian
Vision-driven autonomous river following by Unmanned Aerial Vehicles is critical for applications such as rescue, surveillance, and environmental monitoring, particularly in dense…
Physical Reservoir Computing in Hook-Shaped Rover Wheel Spokes for Real-Time Terrain Identification
Xiao Jin, Zihan Wang, Zhenhua Yu +3
Effective terrain detection in unknown environments is crucial for safe and efficient robotic navigation. Traditional methods often rely on computationally intensive data processin…
Flying on Point Clouds with Reinforcement Learning
Guangtong Xu, Tianyue Wu, Zihan Wang +2
A long-cherished vision of drones is to autonomously traverse through clutter to reach every corner of the world using onboard sensing and computation. In this paper, we combine on…