5 papers
Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
Boxuan Zhang, Weipu Zhang, Zhaohan Feng +4
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit substantial heterogeneity in both observati…
SPGrasp: Spatiotemporal Prompt-driven Grasp Synthesis in Dynamic Scenes
Yunpeng Mei, Hongjie Cao, Yinqiu Xia +4
Real-time interactive grasp synthesis for dynamic objects remains challenging as existing methods fail to achieve low-latency inference while maintaining promptability. To bridge t…
Multi-agent Embodied AI: Advances and Future Directions
Zhaohan Feng, Ruiqi Xue, Lei Yuan +7
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physica…
Time-optimal Flight in Cluttered Environments via Safe Reinforcement Learning
Wei Xiao, Zhaohan Feng, Ziyu Zhou +3
This paper addresses the problem of guiding a quadrotor through a predefined sequence of waypoints in cluttered environments, aiming to minimize the flight time while avoiding coll…
Learning Hybrid Policies for MPC with Application to Drone Flight in Unknown Dynamic Environments
Zhaohan Feng, Jie Chen, Wei Xiao +3
In recent years, drones have found increased applications in a wide array of real-world tasks. Model predictive control (MPC) has emerged as a practical method for drone flight con…