# Robot Learning & Embodied AI Domain: Artificial Intelligence · 264 papers indexed · newest 2026-10-29 Vision-language-action models, large-scale imitation learning, sim-to-real transfer, dexterous manipulation and humanoid control. Key concepts: vision-language-action, robot learning, imitation learning, sim-to-real, humanoid, dexterous manipulation, robot foundation model, diffusion policy ## Most influential - **[Imitation Learning](https://space-kitty.com/papers/doi:10.1145/3054912)**. Ahmed majeed Hussein, Mohamed Medhat Gaber, Eyad Elyan et al. · 2017 · ACM Computing Surveys (doi:10.1145/3054912 · 1,059 citations). Source: - **[Policy search for motor primitives in robotics](https://space-kitty.com/papers/doi:10.1007/s10994-010-5223-6)**. Jens Kober, Jan Peters · 2010 · Machine Learning (doi:10.1007/s10994-010-5223-6 · 477 citations). Source: - **[PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning](https://space-kitty.com/papers/arxiv:1809.03531)**. Guillaume Sartoretti, Justin H. Kerr, Yunfei Shi et al. · 2019 · IEEE Robotics and Automation Letters (arXiv:1809.03531 · doi:10.1109/lra.2019.2903261 · 424 citations). Source: > Multi-agent path finding (MAPF) is an essential component of many large-scale, real-world robot deployments, from aerial swarms to warehouse automation. However, despite the community's continued efforts, most state-of-the-art MAPF planners still rely on centralized planning and scale poorly past a few hundred agents. Such planning approaches are maladapted to real-world deployments, where noise and uncertainty often require paths be recomputed online, which is impossible when planning times are in seconds to minutes. We present PRIMAL, a novel framework for MAPF that combines reinforcement an… - **[Learning and Reproduction of Gestures by Imitation](https://space-kitty.com/papers/doi:10.1109/mra.2010.936947)**. Sylvain Calinon, Florent D'halluin, Eric L. Sauser et al. · 2010 · IEEE Robotics & Automation Magazine (doi:10.1109/mra.2010.936947 · 461 citations). Source: - **[RLBench: The Robot Learning Benchmark & Learning Environment](https://space-kitty.com/papers/arxiv:1909.12271)**. Stephen James, Zicong Ma, David Rovick Arrojo et al. · 2020 · IEEE Robotics and Automation Letters (arXiv:1909.12271 · doi:10.1109/lra.2020.2974707 · 403 citations). Source: > We present a challenging new benchmark and learning-environment for robot learning: RLBench. The benchmark features 100 completely unique, hand-designed tasks ranging in difficulty, from simple target reaching and door opening, to longer multi-stage tasks, such as opening an oven and placing a tray in it. We provide an array of both proprioceptive observations and visual observations, which include rgb, depth, and segmentation masks from an over-the-shoulder stereo camera and an eye-in-hand monocular camera. Uniquely, each task comes with an infinite supply of demos through the use of motion p… - **[An Algorithmic Perspective on Imitation Learning](https://space-kitty.com/papers/arxiv:1811.06711)**. Takayuki Osa, Joni Pajarinen, Gerhard M. Neumann et al. · 2018 · Foundations and Trends in Robotics (arXiv:1811.06711 · doi:10.1561/2300000053 · 405 citations). Source: > As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms develope… - **[Smart Industrial Robot Control Trends, Challenges and Opportunities within Manufacturing](https://space-kitty.com/papers/doi:10.3390/app12020937)**. Jānis Ārents, Modris Greitāns · 2022 · Applied Sciences (doi:10.3390/app12020937 · 324 citations). Source: > Industrial robots and associated control methods are continuously developing. With the recent progress in the field of artificial intelligence, new perspectives in industrial robot control strategies have emerged, and prospects towards cognitive robots have arisen. AI-based robotic systems are strongly becoming one of the main areas of focus, as flexibility and deep understanding of complex manufacturing processes are becoming the key advantage to raise competitiveness. This review first expresses the significance of smart industrial robot control in manufacturing towards future factories by l… > _Abstract excerpt by Jānis Ārents et al., CC-BY, https://doi.org/10.3390/app12020937; truncated._ - **[Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://space-kitty.com/papers/arxiv:2301.04195)**. Mayank Mittal, Calvin Yu, Qinxi Yu et al. · 2023 · IEEE Robotics and Automation Letters (arXiv:2301.04195 · doi:10.1109/lra.2023.3270034 · 269 citations). Source: > We present Orbit, a unified and modular framework for robot learning powered by NVIDIA Isaac Sim. It offers a modular design to easily and efficiently create robotic environments with photo-realistic scenes and high-fidelity rigid and deformable body simulation. With Orbit, we provide a suite of benchmark tasks of varying difficulty -- from single-stage cabinet opening and cloth folding to multi-stage tasks such as room reorganization. To support working with diverse observations and action spaces, we include fixed-arm and mobile manipulators with different physically-based sensors and motion … - **[Dynamic movement primitives in robotics: A tutorial survey](https://space-kitty.com/papers/arxiv:2102.03861)**. Matteo Saveriano, Fares J. Abu‐Dakka, Aljaž Kramberger et al. · 2023 · The International Journal of Robotics Research (arXiv:2102.03861 · doi:10.1177/02783649231201196 · 267 citations). Source: > Biological systems, including human beings, have the innate ability to perform complex tasks in versatile and agile manner. Researchers in sensorimotor control have tried to understand and formally define this innate property. The idea, supported by several experimental findings, that biological systems are able to combine and adapt basic units of motion into complex tasks finally lead to the formulation of the motor primitives theory. In this respect, Dynamic Movement Primitives (DMPs) represent an elegant mathematical formulation of the motor primitives as stable dynamical systems, and are w… - **[Human – robot interaction review and challenges on task planning and programming](https://space-kitty.com/papers/doi:10.1080/0951192x.2015.1130251)**. Panagiota Tsarouchi, Sotiris Makris, George Chryssolouris · 2016 · International Journal of Computer Integrated Manufacturing (doi:10.1080/0951192x.2015.1130251 · 376 citations). Source: - **[One-Shot Imitation Learning](https://space-kitty.com/papers/openalex:W2963094133)**. Yan Duan, Marcin Andrychowicz, Bradly C. Stadie et al. · 2017 · neural information processing systems (372 citations). Source: - **[A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://space-kitty.com/papers/arxiv:2309.02473)**. Maryam Zare, Parham Mohsenzadeh Kebria, Abbas Khosravi et al. · 2024 · IEEE Transactions on Cybernetics (arXiv:2309.02473 · doi:10.1109/tcyb.2024.3395626 · 229 citations). Source: > In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments, such as autonomous driving, aerial robotics, and natural language processing. As a consequence, programming their behaviors manually or defining their behavior through reward functions (as done in reinforcement learning (RL)) has become exceedingly difficult. This is because such environments require a high degree of flexibility and adaptability, making it c… - **[One-Shot Visual Imitation Learning via Meta-Learning](https://space-kitty.com/papers/arxiv:1709.04905)**. Chelsea Finn, Tianhe Yu, Tianhao Zhang et al. · 2017 (arXiv:1709.04905 · 341 citations). Source: > In order for a robot to be a generalist that can perform a wide range of jobs, it must be able to acquire a wide variety of skills quickly and efficiently in complex unstructured environments. High-capacity models such as deep neural networks can enable a robot to represent complex skills, but learning each skill from scratch then becomes infeasible. In this work, we present a meta-imitation learning method that enables a robot to learn how to learn more efficiently, allowing it to acquire new skills from just a single demonstration. Unlike prior methods for one-shot imitation, our method can … - **[Imitation Learning of Positional and Force Skills Demonstrated via Kinesthetic Teaching and Haptic Input](https://space-kitty.com/papers/doi:10.1163/016918611x558261)**. Petar S. Kormushev, Sylvain Calinon, Darwin G. Caldwell · 2011 · Advanced Robotics (doi:10.1163/016918611x558261 · 279 citations). Source: - **[A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://space-kitty.com/papers/arxiv:2101.01993)**. Zeyu Zhu, Huijing Zhao · 2021 · IEEE Transactions on Intelligent Transportation Systems (arXiv:2101.01993 · doi:10.1109/tits.2021.3134702 · 240 citations). Source: > Autonomous driving (AD) agents generate driving policies based on online perception results, which are obtained at multiple levels of abstraction, e.g., behavior planning, motion planning and control. Driving policies are crucial to the realization of safe, efficient and harmonious driving behaviors, where AD agents still face substantial challenges in complex scenarios. Due to their successful application in fields such as robotics and video games, the use of deep reinforcement learning (DRL) and deep imitation learning (DIL) techniques to derive AD policies have witnessed vast research effor… ## Newest - **[Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection](https://space-kitty.com/papers/arxiv:2610.39076)**. Li Guan, Rachael Granberry, Sahar Aseeri et al. · 2026 (arXiv:2610.39076). Source: - **[OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation](https://space-kitty.com/papers/arxiv:2610.39287)**. Junli Liu, Zhongrui You, Chenhui Li et al. · 2026 (arXiv:2610.39287). Source: - **[SONIC-K1: Porting a Universal Humanoid Motion Tracker to a Small Humanoid on a Single GPU](https://space-kitty.com/papers/arxiv:2610.39327)**. Kyrylo Kolesnichenko, Jong-Hoon Kim · 2026 (arXiv:2610.39327). Source: - **[UMI-Live for In-The-Wild Bimanual Robotics Data Collection](https://space-kitty.com/papers/arxiv:2610.39385)**. Govind Velamoor, Adrian Lin, Sam Jung et al. · 2026 (arXiv:2610.39385). Source: - **[ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning](https://space-kitty.com/papers/arxiv:2610.39429)**. Neel Jawale, Stephan Pleines, Soha Pouya et al. · 2026 (arXiv:2610.39429). Source: - **[Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning](https://space-kitty.com/papers/arxiv:2610.39451)**. Shota Nomura, Takayuki Osa, Yasuhiro Kato et al. · 2026 (arXiv:2610.39451). Source: - **[Same Label, Different Interface: Beyond Action-Space Labels in Robot Learning](https://space-kitty.com/papers/arxiv:2610.38104)**. Arshia Sangwan, Zhongyang Zhang · 2026 (arXiv:2610.38104). Source: - **[Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation](https://space-kitty.com/papers/arxiv:2610.38199)**. Greta Perez-Haiek, Luca Macesanu, Kevin Angers et al. · 2026 (arXiv:2610.38199). Source: - **[CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data](https://space-kitty.com/papers/arxiv:2610.38221)**. Jiuyi Xu, Meida Chen, Yang Ye et al. · 2026 (arXiv:2610.38221). Source: - **[SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery](https://space-kitty.com/papers/arxiv:2610.38234)**. Xucheng Wang, Zhizhou Yang, Sung Eun Kim et al. · 2026 (arXiv:2610.38234). Source: --- Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.