Zhennan Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhennan Jiang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Dongjie Yu
The University of Hong Kong
2 shared publications - Chao Yu
Tsinghua University
1 shared publication - Dongbin Zhao
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Haoran Li
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
1 shared publication - Huanyu Li
Shanghai Qi Zhi Institute, Shanghai, China
1 shared publication - Huazhe Xu
Tsinghua University
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12240-12247
World4RL: Diffusion World Models for Policy Refinement With Reinforcement Learning for Robotic Manipulation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 12240-12247
World4RL: Diffusion World Models for Policy Refinement With Reinforcement Learning for Robotic Manipulation
- 22 July 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 11 (116) , eaed6267
Performant robotic manipulation with real-world reinforcement learning
Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass skilled human operators. We present a real-world reinforcement learning (RL) framework, RL-100, for achieving complete task success under a predefined evaluation protocol built on diffusion visuomotor policies. RL-100 unifies imitation and RL under a single clipped proximal policy optimization surrogate objective applied in the denoising process, yielding conservative, stable improvements across offline and online stages. To meet deployment latency, a lightweight consistency distillation compresses multistep diffusion into a one-step controller for high-frequency control. The framework is task, embodiment, and representation agnostic and supports both single-action and action-chunking control. We evaluated RL-100 on eight diverse real-robot tasks, from pushing and bowling to pouring, cloth folding, unscrewing, multistage juicing, and long-horizon box folding. Under our predefined protocol, RL-100 achieved 100% success in the evaluated trials (1000 of 1000 episodes), including up to 250 of 250 consecutive trials on one task. It matched or surpassed expert teleoperators in time to completion. Without retraining, a single policy attained ∼90% zero-shot success under environmental and dynamics shifts, adapted in a few-shot regime to substantial task variations (86.7%), and remained robust to human perturbations (about 96%). Our juicing robot served customers continuously for about 7 hours without failure when deployed zero-shot in a shopping mall. These results suggest a potential path to deployable robot learning by starting from human priors, aligning training objectives with human-grounded metrics, and reliably extending performance beyond human demonstrations.
- 22 July 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Robotics
- Vol. 11 (116) , eaed6267
Performant robotic manipulation with real-world reinforcement learning
Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass skilled human operators. We present a real-world reinforcement learning (RL) framework, RL-100, for achieving complete task success under a predefined evaluation protocol built on diffusion visuomotor policies. RL-100 unifies imitation and RL under a single clipped proximal policy optimization surrogate objective applied in the denoising process, yielding conservative, stable improvements across offline and online stages. To meet deployment latency, a lightweight consistency distillation compresses multistep diffusion into a one-step controller for high-frequency control. The framework is task, embodiment, and representation agnostic and supports both single-action and action-chunking control. We evaluated RL-100 on eight diverse real-robot tasks, from pushing and bowling to pouring, cloth folding, unscrewing, multistage juicing, and long-horizon box folding. Under our predefined protocol, RL-100 achieved 100% success in the evaluated trials (1000 of 1000 episodes), including up to 250 of 250 consecutive trials on one task. It matched or surpassed expert teleoperators in time to completion. Without retraining, a single policy attained ∼90% zero-shot success under environmental and dynamics shifts, adapted in a few-shot regime to substantial task variations (86.7%), and remained robust to human perturbations (about 96%). Our juicing robot served customers continuously for about 7 hours without failure when deployed zero-shot in a shopping mall. These results suggest a potential path to deployable robot learning by starting from human priors, aligning training objectives with human-grounded metrics, and reliably extending performance beyond human demonstrations.