Continual Robot Learning

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 42

All topics

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
Jun 24, 2026Zhihao Gu, Lin WangRobot Policy Learning Continual Robot Learning
School of EEE, Nanyang Technological University
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
Jun 22, 2026Ulas Berk Karli, Tesca FitzgeraldContinual Robot Learning Robot Skill Learning
Department of Computer Science Yale University United States
When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning
Jun 16, 2026Nethmi Jayasinghe, Diana Gontero, Amit Ranjan TrivediRobot Policy Learning Continual Robot Learning
Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, IL, USA.
Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning
Jun 14, 2026Shuaike Zhang, Shaokun Wang, Haoyu Tang +2Continual Robot Learning Robot Skill Learning
Harbin Institute of Technology, Shenzhen · Shandong University · Shenzhen Loop Area Institute
AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning
Jun 9, 2026Hang Yin, Yinan Liang, Jiazhao Zhang +4RL for Robotics Continual Robot Learning
Tsinghua University, Beijing 100084, China · Galbot Robotics, Beijing, China · Peking University, Beijing 100871, China +1
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
May 31, 2026Rufeng Chen, Yue Chang, Xiaqiang Tang +2Continual Robot Learning Embodied Navigation
The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China · Jilin University, Jilin, China
Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
May 29, 2026Navin Sriram Ravie, Andrew Jong, Krrish Jain +4Continual Robot Learning Mobile Robotics
Department of Engineering Design, Indian Institute of Technology, Madras · Robotics Institute, Carnegie Mellon University
Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
May 27, 2026Julia Hindel, Simon Bultmann, Houman Masnavi +2Continual Robot Learning Robot Navigation
Department of Computer Science, University of Freiburg, Germany.
Can VLA Models Learn from Real-World Data Continually without Forgetting?
May 26, 2026Jiarun Zhu, Yijun Hong, Xiaoquan Sun +5Continual Robot Learning Continual Learning for VLA Models
1HKU · 5SUSTech · 2INFIFORCE +3
Beyond Predefined Learning Objects: A Thinking-Learning Interaction Model for Up-to-Date Autonomous Robot Learning
May 17, 2026Hong SuRobot Policy Learning Continual Robot Learning
School of Computer Science, Chengdu University of Information Technology, Chengdu, China
An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments
Apr 24, 2026Hong SuContinual Robot Learning Robot Skill Learning
School of Computer Science, Chengdu University of Information Technology, Chengdu, China.
Robotic Ultra-Long-Horizon Manipulation Skills via Human-guided Lifelong Code Generation
Sep 23, 2025Yuan Meng, Zhenguo Sun, Max Fest +4Long-Horizon Robotic Manipulation Robot Skill Learning
School of Computation, Information and Technology Technical University of Munich Munich, Germany · Beijing Academy of Artificial Intelligence (BAAI) Beijing, China · The State Key Laboratory for Novel Software Technology Nanjing University Suzhou, China

Jun 24, 2026, cs.ROJ/K move · Enter open · S save

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective

Zhihao Gu, Lin Wang

School of EEE, Nanyang Technological University

Robot Policy Learning Continual Robot Learning Robot Skill Learning Mixture of Experts Continual Learning Robotic Manipulation

Open paper AskPDF arXiv

Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge. Previous works alleviate the catastrophic forgetting problem by parameter-efficient fine-tuning for single-task adaptation. However, they fail to extract reusable skills and model the interaction with other skills effectively. Recent works try to address these issues by learning prompts. Differently, this paper presents an architectural perspective on the Lifelong Mixture of Dynamic Experts (\textit{LiMoDE}), a novel two-stage learning scheme for lifelong robot manipulation. Specifically, a dynamic MoE structure is first proposed in the multi-task pre-training stage to learn prior knowledge, where a varied number of heterogeneous experts are activated based on the motion information to address different short-term manipulations. Subsequently, in the task adaptation stage, we design a lifelong MoE adaptation mechanism % (LiMoEAM) that learns lifelong experts and dynamically combines them with frozen ones for new tasks, facilitating the knowledge transfer during adaptation. The proposed \textit{LiMoDE} is evaluated on both the simulated lifelong learning benchmark and real-world tasks. Extensive experiments demonstrate its effectiveness in achieving superior performance and strong lifelong adaptation by introducing a moderate number of additional trainable parameters and inference overhead.

Momentum

Related topics

Latest papers 42