Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address this, current approaches employ expert demonstrations in the form of state-action pairs, which are difficult to obtain for real-world settings such as learning from videos. In this paper, we move toward a more realistic setting and explore state-only imitation learning. To tackle this setting, we train an inverse dynamics model and use it to predict actions for state-only demonstrations. The inverse dynamics model and the policy are trained jointly. Our method performs on par with state-action approaches and considerably outperforms RL alone. By not relying on expert actions, we are able to learn from demonstrations with different dynamics, morphologies, and objects. Videos available at https://people.eecs.berkeley.edu/~ilija/soil .
Optimizing behaviors for dexterous manipulation has been a longstanding challenge in robotics, with a variety of methods from model-based control to model-free reinforcement learning having been previously explored in literature. Perhaps one of the most powerful techniques to learn complex manipulation strategies is imitation learning. However, collecting and learning from demonstrations in dexterous manipulation is quite challenging. The complex, high-dimensional action-space involved with multi-finger control often leads to poor sample efficiency of learning-based methods. In this work, we p…
While significant progress has been made on understanding hand-object interactions in computer vision, it is still very challenging for robots to perform complex dexterous manipulation. In this paper, we propose a new platform and pipeline DexMV (Dexterous Manipulation from Videos) for imitation learning. We design a platform with: (i) a simulation system for complex dexterous manipulation tasks with a multi-finger robot hand and (ii) a computer vision system to record large-scale demonstrations of a human hand conducting the same tasks. In our novel pipeline, we extract 3D hand and object pos…
We propose to perform imitation learning for dexterous manipulation with multi-finger robot hand from human demonstrations, and transfer the policy to the real robot hand. We introduce a novel single-camera teleoperation system to collect the 3D demonstrations efficiently with only an iPad and a computer. One key contribution of our system is that we construct a customized robot hand for each user in the physical simulator, which is a manipulator resembling the same kinematics structure and shape of the operator's hand. This provides an intuitive interface and avoid unstable human-robot hand r…
Dexterous Manipulation through Imitation Learning: A Survey
Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System（天津智能集群技术与系统重点实验室）；School of Electrical and Information Engineering（电气与信息工程学院）；Shandong University（山东大学）；State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）；Division of Robotics, Perception and Learning（机器人、感知与学习 division）；School of Control Science and Engineering（控制科学与工程学院）；Massachusetts Institute of Technology（麻省理工学院）；School of Computer Science（计算机科学学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence（人工智能学院）
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system like friction coefficients and an object's appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coo…
We propose a sim-to-real framework for dexterous manipulation which can generalize to new objects of the same category in the real world. The key of our framework is to train the manipulation policy with point cloud inputs and dexterous hands. We propose two new techniques to enable joint learning on multiple objects and sim-to-real generalization: (i) using imagined hand point clouds as augmented inputs; and (ii) designing novel contact-based rewards. We empirically evaluate our method using an Allegro Hand to grasp novel objects in both simulation and real world. To the best of our knowledge…
University of California at Berkeley（加州大学伯克利分校）；Technische Universität Berlin（柏林工业大学）
Dexterous multi-fingered hands can accomplish fine manipulation behaviors that are infeasible with simple robotic grippers. However, sophisticated multi-fingered hands are often expensive and fragile. Low-cost soft hands offer an appealing alternative to more conventional devices, but present considerable challenges in sensing and actuation, making them difficult to apply to more complex manipulation tasks. In this paper, we describe an approach to learning from demonstration that can be used to train soft robotic hands to perform dexterous manipulation tasks. Our method uses object-centric de…
DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
DexRobot Co. Ltd.（德克斯机器人有限公司）；University of Michigan（密歇根大学）；Shanghai Jiao Tong University（上海交通大学）；Chongqing University（重庆大学）；East China University of Science and Technology（东华大学）
A Wearable Robotic Hand for Hand-over-Hand Imitation Learning
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Shanghai AI Lab（上海人工智能实验室）；Shanghai Qi Zhi Institute（上海期智研究院）
UC Berkeley（加州大学伯克利分校）；Meta AI Research（Meta人工智能研究院）；University of Washington（华盛顿大学）
Complex and contact-rich robotic manipulation tasks, particularly those that involve multi-fingered hands and underactuated object manipulation, present a significant challenge to any control method. Methods based on reinforcement learning offer an appealing choice for such settings, as they can enable robots to learn to delicately balance contact forces and dexterously reposition objects without strong modeling assumptions. However, running reinforcement learning on real-world dexterous manipulation systems often requires significant manual engineering. This negates the benefits of autonomous…
University of Washington（华盛顿大学）；OpenAI；University of California Berkeley（加州大学伯克利分校）；Istituto Italiano di Tecnologia（意大利理工学院）
Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotic…
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…
Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation
Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo（智能系统与信息学实验室，信息科学与技术研究生院，东京大学）
Dexterous manipulation of arbitrary objects, a fundamental daily task for humans, has been a grand challenge for autonomous robotic systems. Although data-driven approaches using reinforcement learning can develop specialist policies that discover behaviors to control a single object, they often exhibit poor generalization to unseen ones. In this work, we show that policies learned by existing reinforcement learning algorithms can in fact be generalist when combined with multi-task learning and a well-chosen object representation. We show that a single generalist policy can perform in-hand man…
TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
School of Computer Science and Engineering, Sun Yat-sen University, China（中山大学计算机科学与工程学院）；Stanford University, USA（斯坦福大学）；Imperial College London, UK（伦敦帝国理工学院）
Dexterous manipulation with a multi-finger hand is one of the most challenging problems in robotics. While recent progress in imitation learning has largely improved the sample efficiency compared to Reinforcement Learning, the learned policy can hardly generalize to manipulate novel objects, given limited expert demonstrations. In this paper, we propose to learn dexterous manipulation using large-scale demonstrations with diverse 3D objects in a category, which are generated from a human grasp affordance model. This generalizes the policy to novel object instances within the same category. To…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Hong Kong University of Science and Technology（香港科技大学）
We propose the Dexterous Manipulation Graph as a tool to address in-hand manipulation and reposition an object inside a robot's end-effector. This graph is used to plan a sequence of manipulation primitives so to bring the object to the desired end pose. This sequence of primitives is translated into motions of the robot to move the object held by the end-effector. We use a dual arm robot with parallel grippers to test our method on a real system and show successful planning and execution of in-hand manipulation.
The discontinuities and multi-modality introduced by contacts make manipulation planning challenging. Many previous works avoid this problem by pre-designing a set of high-level motion primitives like grasping and pushing. However, such motion primitives are often not adequate to describe dexterous manipulation motions. In this work, we propose a method for dexterous manipulation planning at a more primitive level. The key idea is to use contact modes to guide the search in a sampling-based planning framework. Our method can automatically generate contact transitions and motion trajectories un…
High resolution tactile sensors are often bulky and have shape profiles that make them awkward for use in manipulation. This becomes important when using such sensors as fingertips for dexterous multi-fingered hands, where boxy or planar fingertips limit the available set of smooth manipulation strategies. High resolution optical based sensors such as GelSight have until now been constrained to relatively flat geometries due to constraints on illumination geometry.Here, we show how to construct a rounded fingertip that utilizes a form of light piping for directional illumination. Our sensors c…
Dexterous multi-fingered hands can provide robots with the ability to flexibly perform a wide range of manipulation skills. However, many of the more complex behaviors are also notoriously difficult to control: Performing in-hand object manipulation, executing finger gaits to move objects, and exhibiting precise fine motor skills such as writing, all require finely balancing contact forces, breaking and reestablishing contacts repeatedly, and maintaining control of unactuated objects. Learning-based techniques provide the appealing possibility of acquiring these skills directly from data, but …
KTH Royal Institute of Technology（瑞典皇家理工学院）；Yale University（耶鲁大学）
This work focuses on the problem of in-hand manipulation and regrasping of objects with parallel grippers. We propose Dexterous Manipulation Graph (DMG) as a representation on which we define planning for in-hand manipulation and regrasping. The DMG is a disconnected undirected graph that represents the possible motions of a finger along the object's surface. We formulate the in-hand manipulation and regrasping problem as a graph search problem from the initial to the final configuration. The resulting plan is a sequence of coordinated in-hand pushing and regrasping movements. We propose a dua…
Dexterous manipulation tasks often require contact switching, where fingers make and break contact with the object. We propose a method that plans trajectories for dexterous manipulation tasks involving contact switching using contact-implicit trajectory optimization (CITO) augmented with a high-level discrete contact sequence planner. We first use the high-level planner to find a sequence of finger contact switches given a desired object trajectory. With this contact sequence plan, we impose additional constraints in the CITO problem. We show that our method finds trajectories approximately 7…
This paper presents Contact Mode Guided Manipulation Planning (CMGMP) for 3D quasistatic and quasidynamic rigid body motion planning in dexterous manipulation. The CMGMP algorithm generates hybrid motion plans including both continuous state transitions and discrete contact mode switches, without the need for pre-specified contact sequences or pre-designed motion primitives. The key idea is to use automatically enumerated contact modes of environment-object contacts to guide the tree expansions during the search. Contact modes automatically synthesize manipulation primitives, while the samplin…
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University（机械系统与振动国家重点实验室，机械工程学院，上海交通大学）；Shanghai Key Laboratory of Intelligent Robotics, Meta Robotics Institute, Shanghai Jiao Tong University, Shanghai 200240, China（智能机器人上海市重点实验室，元机器人研究院，上海交通大学，上海200240，中国）；The University of Tokyo（东京大学）
