Learning from demonstration (LfD) provides a convenient means to equip robots with dexterous skills when demonstration can be obtained in robot intrinsic coordinates. However, the problem of compounding errors in long and complex skills reduces its wide deployment. Since most such complex skills are composed of smaller movements that are combined, considering the target skill as a sequence of compact motor primitives seems reasonable. Here the problem that needs to be tackled is to ensure that a motor primitive ends in a state that allows the successful execution of the subsequent primitive. In this study, we focus on this problem by proposing to learn an explicit correction policy when the expected transition state between primitives is not achieved. The correction policy is itself learned via behavior cloning by the use of a state-of-the-art movement primitive learning architecture, Conditional Neural Motor Primitives (CNMPs). The learned correction policy is then able to produce diverse movement trajectories in a context dependent way. The advantage of the proposed system over learning the complete task as a single action is shown with a table-top setup in simulation, where an object has to be pushed through a corridor in two steps. Then, the applicability of the proposed method to bi-manual knotting in the real world is shown by equipping an upper-body humanoid robot with the skill of making knots over a bar in 3D space. The experiments show that the robot can perform successful knotting even when the faced correction cases are not part of the human demonstration set.
Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data
Technical University of Darmstadt（德累斯顿技术大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Robotics Institute Germany (RIG)（德国机器人研究所）；Centre for Cognitive Science（认知科学研究中心）；Honda Research Institute Europe GmbH（本田欧洲研究院）
Learning Fine Pinch-Grasp Skills using Tactile Sensing from A Few Real-world Demonstrations
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Touchlab Limited（Touchlab有限公司）；Department of Engineering Mathematics, University of Bristol（布里斯托尔大学工程数学系）；Department of Computer Science, University College London（伦敦大学学院计算机科学系）
COFFAIL: A Dataset of Successful and Anomalous Robot Skill Executions in the Context of Coffee Preparation
Division of Systems and Control, Chalmers University of Technology（系统与控制系，楚姆勒斯理工大学）；Bonn-Rhein-Sieg University of Applied Sciences（波恩-莱茵-西弗大学）；Autonomous Systems Group, Bonn-Rhein-Sieg University of Applied Sciences（自主系统组，波恩-莱茵-西弗大学）
Istituto Italiano di Tecnologia（意大利技术研究院）；Idiap Research Institute（Idiap研究所）
Bimanual operations in humanoids offer the possibility to carry out more than one manipulation task at the same time, which in turn introduces the problem of task prioritization. We address this problem from a learning from demonstration perspective, by extending the Task-Parameterized Gaussian Mixture Model (TP-GMM) to Jacobian and null space structures. The proposed approach is tested on bimanual skills but can be applied in any scenario where the prioritization between potentially conflicting tasks needs to be learned. We evaluate the proposed framework in: two different tasks with humanoid…
Adapt as You Say: Online Interactive Bimanual Skill Adaptation via Human Language Feedback
Collaborative and Versatile Robots (CLOVER) Laboratory, T-Stone Robotics Institute, The Chinese University of Hong Kong（香港中文大学T-Stone机器人研究所协作与多功能机器人（CLOVER）实验室）；Department of Mechanical and Aerospace Engineering, University of California, Los Angeles（加州大学洛杉矶分校机械与航空航天工程系）；Department of Advanced Robotics, Istituto Italiano di Tecnologia（意大利技术研究院先进机器人系）
ForwardDLO: Model-Based Bimanual Shape Matching of Unconstrained Deformable Linear Objects
Technical University of Darmstadt（达姆施塔特工业大学）；Honda Research Institute Europe GmbH（本田欧洲研究院有限公司）；Universidade Estadual de Campinas (UNICAMP)（坎皮纳斯州立大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Robotics Institute Germany (RIG)（德国机器人研究所）；Centre for Cognitive Science（认知科学中心）
University of Southern California（南加州大学）；Meta AI；KAIST（韩国科学技术院）；Georgia Tech（佐治亚理工学院）
We propose an approach for semantic imitation, which uses demonstrations from a source domain, e.g. human videos, to accelerate reinforcement learning (RL) in a different target domain, e.g. a robotic manipulator in a simulated kitchen. Instead of imitating low-level actions like joint velocities, our approach imitates the sequence of demonstrated semantic skills like "opening the microwave" or "turning on the stove". This allows us to transfer demonstrations across environments (e.g. real-world to simulated kitchen) and agent embodiments (e.g. bimanual human demonstration to robotic arm). We …
Ag2x2: Robust Agent-Agnostic Visual Representations for Zero-Shot Bimanual Manipulation
National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI)（国家关键人工智能实验室，北京通用人工智能研究院（BIGAI））；School of Psychological and Cognitive Sciences, Peking University（北京大学心理与认知科学学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Beijing Key Laboratory of Behavior and Mental Health, Peking University（北京行为与心理健康重点实验室，北京大学）；Yuanpei College, Peking University（北京大学元培学院）；Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）；Embodied Intelligence Lab, PKU-Wuhan Institute for Artificial Intelligence（具身智能实验室，北京大学-武汉人工智能研究院）
ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation
Department of Mechanical and Automation Engineering, T-Stone Robotics Institute, The Chinese University of Hong Kong（机械与自动化工程系、T-Stone机器人研究所、香港中文大学）；Hong Kong Center for Logistics Robotics（香港物流机器人中心）；Department of Technological Sciences, Wuhan University（技术科学系、武汉大学）；Idiap Research Institute（Idiap研究所）；Department of Advanced Robotics, Istituto Italiano di Tecnologia（先进机器人系、意大利Istituto Italiano di Tecnologia）
AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Facebook Artificial Intelligence Research（脸书人工智能研究院）
We address the problem of effectively composing skills to solve sparse-reward tasks in the real world. Given a set of parameterized skills (such as exerting a force or doing a top grasp at a location), our goal is to learn policies that invoke these skills to efficiently solve such tasks. Our insight is that for many tasks, the learning process can be decomposed into learning a state-independent task schema (a sequence of skills to execute) and a policy to choose the parameterizations of the skills in a state-dependent manner. For such tasks, we show that explicitly modeling the schema's state…
SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse
National University of Singapore（国立新加坡大学）；Beijing Zhongguancun Academy（北京中关村学院）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Fudan University（复旦大学）；Smart Systems Institute, NUS（NUS智能系统研究所）
RoTri-Diff: A Spatial Robot-Object Triadic Interaction-Guided Diffusion Model for Bimanual Manipulation
School of Computer Science, Nanjing University（南京大学计算机科学学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）
In contrast to humans and animals who naturally execute seamless motions, learning and smoothly executing sequences of actions remains a challenge in robotics. This paper introduces a novel skill-agnostic framework that learns to sequence and blend skills based on differentiable optimization. Our approach encodes sequences of previously-defined skills as quadratic programs (QP), whose parameters determine the relative importance of skills along the task. Seamless skill sequences are then learned from demonstrations by exploiting differentiable optimization layers and a tailored loss formulated…
Institute for AI, Peking University（北京大学人工智能研究院）；Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心）；University College London（伦敦大学学院）；Carnegie Mellon University（卡内基梅隆大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
Achieving human-level dexterity is an important open problem in robotics. However, tasks of dexterous hand manipulation, even at the baby level, are challenging to solve through reinforcement learning (RL). The difficulty lies in the high degrees of freedom and the required cooperation among heterogeneous agents (e.g., joints of fingers). In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects. Specifically, tasks in Bi-DexHands are designed to match di…
University of Michigan（密歇根大学）；Carnegie Mellon University（卡内基梅隆大学）
In order to efficiently learn a dynamics model for a task in a new environment, one can adapt a model learned in a similar source environment. However, existing adaptation methods can fail when the target dataset contains transitions where the dynamics are very different from the source environment. For example, the source environment dynamics could be of a rope manipulated in free-space, whereas the target dynamics could involve collisions and deformation on obstacles. Our key insight is to improve data efficiency by focusing model adaptation on only the regions where the source and target dy…
Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation
TU Darmstadt（达姆施塔特工业大学）；Honda Research Institute Europe（本田欧洲研究所）；Istituto Italiano di Tecnologia（意大利理工学院）；DFKI（德国人工智能研究中心）；Robotics Institute Germany（德国机器人研究所）
Northeastern University（东北大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. A core challenge is to generalize the manipulation skills to objects in different locations. We hypothesize that modeling the relational information in the environment can significantly improve generalization. To achieve this, we propose to (i) decompose the multi-modal dynamics into elemental movement primitives, (ii) parameterize each primitive using a recurrent graph neural network to capture interactions, and (iii) integrate a high-level planner that composes primitives sequ…
Hamlyn Centre for Robotic Surgery, Imperial College London（伦敦帝国理工学院哈姆林机器人手术中心）；Auris Surgical Robotics Inc.（Auris手术机器人公司）；Samsung R&D Institute（三星研发研究院）
This paper presents a multi-robot system for manufacturing personalized medical stent grafts. The proposed system adopts a modular design, which includes: a (personalized) mandrel module, a bimanual sewing module, and a vision module. The mandrel module incorporates the personalized geometry of patients, while the bimanual sewing module adopts a learning-by-demonstration approach to transfer human hand-sewing skills to the robots. The human demonstrations were firstly observed by the vision module and then encoded using a statistical model to generate the reference motion trajectories. During …
Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning
National Key Laboratory of Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；Beijing Academy of Artificial Intelligence, BAAI（北京智源人工智能研究院）
The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert supervision and then distills its experience into a goal-conditioned skill policy with a novel forward consistency loss. In our framework, the role of the expert is only to communicate the goals (i.e., what to imitate) during inference. The learned policy is then employed to mimic the expert (i.e., how to imitate) after seeing just a sequence of images demonst…
Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable objects. In these cases, prior methods use engineered problem-specific solutions, e.g., by instrumenting the environment with additional sensors to measure a proxy for the objective. Such solutions require a significant engineering effort on a per-task basis, and make it impract…
