14 papers
Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation
Chun Gu, Xiaofei Wei, Yiming Chen +4
Large pretrained robot foundation models provide strong priors for manipulation, yet adapting them to target tasks with offline teleoperated demonstrations often fails to cover the…
PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning
Yangang Zou, Jiajun Lu, Weitao Zhou +6
Outcome-based reinforcement learning (RL) post-trains vision--language--action policies using terminal success signals, but assigns the same trajectory-level advantage to every act…
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
Yajie Li, Bozhou Zhang, Chun Gu +5
Video generation models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined fut…
See Tomorrow, Act Today: Foresight-Driven Autonomous Driving
Bozhou Zhang, Nan Song, Yuang Wang +3
Current end-to-end autonomous driving planners are fundamentally reactive: they condition on historical and present observations to predict future actions. We argue that autonomous…
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
Wenyao Zhang, Bozhou Zhang, Zekun Qi +3
Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image forecasting and 3D action prediction…
Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
Bozhou Zhang, Nan Song, Jingyu Li +3
End-to-end autonomous driving methods aim to directly map raw sensor inputs to future driving actions such as planned trajectories, bypassing traditional modular pipelines. While t…
LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving
Nan Song, Bozhou Zhang, Xiatian Zhu +2
Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existi…
Relative Position Matters: Trajectory Prediction and Planning with Polar Representation
Bozhou Zhang, Nan Song, Bingzhao Gao +1
Trajectory prediction and planning in autonomous driving are highly challenging due to the complexity of predicting surrounding agents' movements and planning the ego agent's actio…
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
Bozhou Zhang, Jingyu Li, Nan Song +1
End-to-end autonomous driving has achieved remarkable advancements in recent years. Existing methods primarily follow a perception-planning paradigm, where perception and planning…
DeMo++: Motion Decoupling for Autonomous Driving
Bozhou Zhang, Nan Song, Xiatian Zhu +1
Motion forecasting and planning are tasked with estimating the trajectories of traffic agents and the ego vehicle, respectively, to ensure the safety and efficiency of autonomous d…
ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving
Jingyu Li, Bozhou Zhang, Xin Jin +3
Autonomous driving requires rich contextual comprehension and precise predictive reasoning to navigate dynamic and complex environments safely. Vision-Language Models (VLMs) and Dr…
Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning
Bozhou Zhang, Nan Song, Xin Jin +1
End-to-end autonomous driving unifies tasks in a differentiable framework, enabling planning-oriented optimization and attracting growing attention. Current methods aggregate histo…
Motion Forecasting in Continuous Driving
Nan Song, Bozhou Zhang, Xiatian Zhu +1
Motion forecasting for agents in autonomous driving is highly challenging due to the numerous possibilities for each agent's next action and their complex interactions in space and…
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
Bozhou Zhang, Nan Song, Li Zhang
Accurate motion forecasting for traffic agents is crucial for ensuring the safety and efficiency of autonomous driving systems in dynamically changing environments. Mainstream meth…