Related papers: Learning Extrinsic Dexterity with Parameterized Ma…
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…
Recent studies on quadruped robots have focused on either locomotion or mobile manipulation using a robotic arm. Legged robots can manipulate heavier and larger objects using non-prehensile manipulation primitives, such as planar pushing,…
Grasping is the dominant approach for robot manipulation, but only a single object can be grasped at a time. Nonprehensile manipulation offers richer set of interactions, however state-of-the-art is limited to using the end-effector only.…
Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. To combat these factors and…
Non-prehensile manipulation is essential for handling thin, large, or otherwise ungraspable objects in unstructured settings. Prior planning and search-based methods often rely on ad-hoc manual designs or generate physically unrealizable…
Robotic systems in manufacturing applications commonly assume known object geometry and appearance. This simplifies the task for the 3D perception algorithms and allows the manipulation to be more deterministic. However, those approaches…
In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…
It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functions that map a human's low-dimensional inputs (e.g., via a…
In complex scenarios where typical pick-and-place techniques are insufficient, often non-prehensile manipulation can ensure that a robot is able to fulfill its task. However, non-prehensile manipulation is challenging due to its…
Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it…
Long-horizon contact-rich tasks are challenging to learn with reinforcement learning, due to ineffective exploration of high-dimensional state spaces with sparse rewards. The learning process often gets stuck in local optimum and demands…
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…
Autonomous dual-arm manipulation is an essential skill to deploy robots in unstructured scenarios. However, this is a challenging undertaking, particularly in terms of perception and planning. Unstructured scenarios are full of objects with…
End-to-end reinforcement learning techniques are among the most successful methods for robotic manipulation tasks. However, the training time required to find a good policy capable of solving complex tasks is prohibitively large. Therefore,…
Although, in the task of grasping via a data-driven method, closed-loop feedback and predicting 6 degrees of freedom (DoF) grasp rather than conventionally used 4DoF top-down grasp are demonstrated to improve performance individually, few…
Humans can determine a proper strategy to grasp an object according to the measured physical attributes or the prior knowledge of the object. This paper proposes an approach to determining the strategy of dexterous grasping by using an…
A shared grasp is a grasp formed by contacts between the manipulated object and both the robot hand and the environment. By trading off hand contacts for environmental contacts, a shared grasp requires fewer contacts with the hand, and…
Robotics grasping refers to the task of making a robotic system pick an object by applying forces and torques on its surface. Despite the recent advances in data-driven approaches, grasping remains an unsolved problem. Most of the works on…
Retrieving objects from clutters is a complex task, which requires multiple interactions with the environment until the target object can be extracted. These interactions involve executing action primitives like grasping or pushing as well…
Learning diverse dexterous manipulation behaviors with assorted objects remains an open grand challenge. While policy learning methods offer a powerful avenue to attack this problem, they require extensive per-task engineering and…