7 papers · 1 filter
PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
Yupeng Zheng, Xiang Li, Songen Gu +12
Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency and a lack of high-level know…
Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
Yinfeng Gao, Deqing Liu, Qichao Zhang +7
Current Vision-Language-Action (VLA) paradigms in end-to-end autonomous driving rely on offline training from static datasets, leaving them vulnerable to distribution shift. Recent…
PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning
Yinfeng Gao, Qichao Zhang, Deqing Liu +8
End-to-end autonomous driving policies based on Imitation Learning (IL) often struggle in closed-loop execution due to the misalignment between inadequate open-loop training object…
WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving
Pengxuan Yang, Ben Lu, Zhongpu Xia +7
Latent World Models enhance scene representation through temporal self-supervised learning, presenting a perception annotation-free paradigm for end-to-end autonomous driving. Howe…
TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Data
Deqing Liu, Yinfeng Gao, Deheng Qian +9
Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deplo…
Dream to Drive with Predictive Individual World Model
Yinfeng Gao, Qichao Zhang, Da-wei Ding +1
It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) of…