Jul 2026
Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Chassis Adaptation
DynaDreamer is proposed, a dynamics-augmented Dreamer-style reinforcement learning method to address the problem of egocentric driving by augmenting the WM with an explicit ego-dynamics prior, and improves task success rates over the strongest baseline.
Zhidong Wang, Jingsong Liang, Zirui Li et al.
· arXiv.org · 0 citations