Robotic manipulation has advanced rapidly in mapping visual observations and language instructions to actions. However, reliable manipulation in open-world environments requires robust spatial understanding: the ability to identify targets in complex layouts (spatial reasoning) and adapt to scenes that continuously evo...
Jing-He Wang, Xin-Rui Cao, Duo Wu et al.· 0 citations
This work introduces eVTA, which learns success probabilities from mixed-quality policy rollouts through temporal-difference-style bootstrapping, without expert demonstrations or intermediate annotations, and introduces RL with Evolving Rewards (RLER), a closed-loop framework that adapts eVTA using newly collected roll...
Duo Wu, Hai-Feng Wang, Rongwei Lu et al.· arXiv.org· 1 citation
GeniWorld is presented, an interactive world model for robots that generalizes robustly across unseen scenarios by explicitly decoupling embodiment kinematics from environmental dynamics, and generates diverse manipulation trajectories within the world model, improving downstream policy performance and robustness in co...