DemoStream is a Task and Motion Planning (TAMP) system that uses GPU‑accelerated batched sampling to generate high‑quality demonstrations for robotic manipulation. By optimizing demonstration quality and exploring many solutions in parallel, it improves behavior cloning success rates and enables real‑world demo collection at an average of 66 demos per hour. The approach evaluates different action spaces, cost functions, and batch sizes in simulation to understand their impact on downstream policy performance.
By Caelan Garrett, Neel Jawale, Fabio Ramos
Sim-and-Human Co-training (SimHum) is a method that combines simulation and human demonstration data to train bimanual manipulation policies. It first extracts kinematic priors from simulation and visual priors from human observations, then fine‑tunes on a small real‑robot dataset. With only 80 real‑robot episodes per task, SimHum achieves 62.5% success on out‑of‑distribution scenes across four tabletop tasks, outperforming real‑only training by 53.7% and improving the best single‑source baseline by 35.0% in a matched‑time study.
By Kaipeng Fang, Weiqing Liang, Yuyang Li, Ji Zhang, Pengpeng Zeng, Heng Tao Shen, Jingkuan Song, Lianli Gao
arXiv:2601. 21718v2 Announce Type: replace-cross Abstract: Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited.
By Lukas Sch\"afer, Pallavi Choudhury, Abdelhak Lemkhenter, Chris Lovett, Somjit Nath, Luis Fran\c{c}a, Matheus Ribeiro Furtado de Mendon\c{c}a, Alex Lamb, Riashat Islam, Siddhartha Sen, John Langford, Katja Hofmann, Sergio Valcarcel Macua
arXiv:2512. 16861v2 Announce Type: replace-cross Abstract: Long-horizon manipulation has been a long-standing challenge in the robotics community.
By Zihan Zhou, Animesh Garg, Ajay Mandlekar, Caelan Garrett
arXiv:2506. 20668v3 Announce Type: replace-cross Abstract: We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data.
By Sungjae Park, Homanga Bharadhwaj, Shubham Tulsiani
arXiv:2608.21204v1 Announce Type: cross
Abstract: Behaviour Cloning (BC) has driven remarkable progress in robot manipulation, yet it is fundamentally limited by its inability to self-improve: a poli...
By Varun Giridhar, Anant Khandelwal, Jeremy A. Collins, Ignat Georgiev, Animesh Garg
EgoSpeedUp is a framework that transfers human manipulation tempo to robot policies by aligning and retiming robot demonstrations using phase-wise tempo estimates derived from human demonstrations. The method improves task success rates by an average of 25 percentage points and reduces successful execution time by 36.5% on two real-world manipulation tasks. It demonstrates that human manipulation tempo can serve as an effective temporal reference for faster and more reliable robot policies.
By Hanbit Oh, Yukiyasu Domae, Takuma Yagi
arXiv:2605. 12236v2 Announce Type: replace-cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.
By Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta
arXiv:2609.37359v1 Announce Type: cross
Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves ou...
By Yifan Kang, Zihan Wang, Zhiwen Fan, Bangya Liu
arXiv:2606. 11901v1 Announce Type: cross Abstract: Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captured by existing benchmarks.
By Tobias J\"ulg, Seongjin Bien, Simon Hilber, Yannik Blei, Pierre Krack, Maximilian Li, Sven Parusel, Rudolf Lioutikov, Florian Walter, Wolfram Burgard
Rewind-IL is a training‑free online safeguard for generative action‑chunked imitation learning policies. It uses a zero‑shot failure detector based on Temporal Inter‑chunk Discrepancy Estimate (TIDE) and a state‑respawning mechanism that returns the robot to a verified safe intermediate state. The system builds a checkpoint library offline with a vision‑language model and monitors self‑consistency online, rewinding execution to the latest safe checkpoint when a failure is detected, thereby improving reliability in long‑horizon manipulation tasks.
By Gehan Zheng, Sanjay Seenivasan, Matthew Johnson-Roberson, Weiming Zhi
Recent progress in large-scale imitation learning for robot manipulation has been driven by leveraging datasets across a wide range of robot embodiments. However, achieving significant cross-embodiment transfer is often still challenging.