Zobrazeno 1 - 10
of 345
pro vyhledávání: '"Dollar, Aaron M."'
Calibrating robots into their workspaces is crucial for manipulation tasks. Existing calibration techniques often rely on sensors external to the robot (cameras, laser scanners, etc.) or specialized tools. This reliance complicates the calibration pr
Externí odkaz:
http://arxiv.org/abs/2403.13144
Autor:
Seewald, Adam, Chancán, Marvin, McCann, Connor M., Noh, Seonghoon, Fallahi, Omeed, Castillo, Hector, Abraham, Ian, Dollar, Aaron M.
This systems paper presents the implementation and design of RB5, a wheeled robot for autonomous long-term exploration with fewer and cheaper sensors. Requiring just an RGB-D camera and low-power computing hardware, the system consists of an experime
Externí odkaz:
http://arxiv.org/abs/2402.08897
Energy-Aware Ergodic Search: Continuous Exploration for Multi-Agent Systems with Battery Constraints
Continuous exploration without interruption is important in scenarios such as search and rescue and precision agriculture, where consistent presence is needed to detect events over large areas. Ergodic search already derives continuous trajectories i
Externí odkaz:
http://arxiv.org/abs/2310.09470
Building hand-object models for dexterous in-hand manipulation remains a crucial and open problem. Major challenges include the difficulty of obtaining the geometric and dynamical models of the hand, object, and time-varying contacts, as well as the
Externí odkaz:
http://arxiv.org/abs/2307.10033
Publikováno v:
IEEE International Conference on Robotics and Automation (ICRA), 2023
Contact can be conceptualized as a set of constraints imposed on two bodies that are interacting with one another in some way. The nature of a contact, whether a point, line, or surface, dictates how these bodies are able to move with respect to one
Externí odkaz:
http://arxiv.org/abs/2303.05565
Modular Active Cell Robots (MACROs) is a design approach in which a large number of linear actuators and passive compliant joints are assembled to create an active structure with a repeating unit cell. Such a mesh-like robotic structure can be actuat
Externí odkaz:
http://arxiv.org/abs/2203.06234
Modular Active Cell Robots (MACROs) are a design paradigm for modular robotic hardware that uses only two components, namely actuators and passive compliant joints. Under the MACRO approach, a large number of actuators and joints are connected to cre
Externí odkaz:
http://arxiv.org/abs/2203.06231
Constraining contacts to remain fixed on an object during manipulation limits the potential workspace size, as motion is subject to the hand's kinematic topology. Finger gaiting is one way to alleviate such restraints. It allows contacts to be freely
Externí odkaz:
http://arxiv.org/abs/2201.07928
Autor:
Morgan, Andrew S., Wen, Bowen, Liang, Junchi, Boularias, Abdeslam, Dollar, Aaron M., Bekris, Kostas
Highly constrained manipulation tasks continue to be challenging for autonomous robots as they require high levels of precision, typically less than 1mm, which is often incompatible with what can be achieved by traditional perception systems. This pa
Externí odkaz:
http://arxiv.org/abs/2106.14070
Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
Autor:
Morgan, Andrew S., Nandha, Daljeet, Chalvatzaki, Georgia, D'Eramo, Carlo, Dollar, Aaron M., Peters, Jan
Publikováno v:
2021 IEEE International Conference on Robotics and Automation (ICRA)
Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance. Meanwhile, their inherent sample efficiency warrants utility for most robo
Externí odkaz:
http://arxiv.org/abs/2103.13842