Zobrazeno 1 - 10
of 55
pro vyhledávání: '"He, Zhanpeng"'
Underactuated manipulators reduce the number of bulky motors, thereby enabling compact and mechanically robust designs. However, fewer actuators than joints means that the manipulator can only access a specific manifold within the joint space, which
Externí odkaz:
http://arxiv.org/abs/2405.14566
Autor:
He, Zhanpeng, Ciocarlie, Matei
We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simula
Externí odkaz:
http://arxiv.org/abs/2309.17227
The choice of a grasp plays a critical role in the success of downstream manipulation tasks. Consider a task of placing an object in a cluttered scene; the majority of possible grasps may not be suitable for the desired placement. In this paper, we s
Externí odkaz:
http://arxiv.org/abs/2304.04100
Autor:
Singi, Siddharth, He, Zhanpeng, Pan, Alvin, Patel, Sandip, Sigurdsson, Gunnar A., Piramuthu, Robinson, Song, Shuran, Ciocarlie, Matei
In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests can lead t
Externí odkaz:
http://arxiv.org/abs/2303.06710
Autor:
He, Zhanpeng, Ciocarlie, Matei
Publikováno v:
IEEE International Conference on Robotics and Automation 2022
Controlling robotic manipulators with high-dimensional action spaces for dexterous tasks is a challenging problem. Inspired by human manipulation, researchers have studied generating and using postural synergies for robot hands to accomplish manipula
Externí odkaz:
http://arxiv.org/abs/2110.01530
We introduce the Universal Manipulation Policy Network (UMPNet) -- a single image-based policy network that infers closed-loop action sequences for manipulating arbitrary articulated objects. To infer a wide range of action trajectories, the policy s
Externí odkaz:
http://arxiv.org/abs/2109.05668
3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial observations are
Externí odkaz:
http://arxiv.org/abs/2011.01968
Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware of the robot has been considered immutable, modeled as part of the envi
Externí odkaz:
http://arxiv.org/abs/2008.04460
Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this problem, recent
Externí odkaz:
http://arxiv.org/abs/2003.04956
Autor:
Yu, Tianhe, Quillen, Deirdre, He, Zhanpeng, Julian, Ryan, Narayan, Avnish, Shively, Hayden, Bellathur, Adithya, Hausman, Karol, Finn, Chelsea, Levine, Sergey
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions
Externí odkaz:
http://arxiv.org/abs/1910.10897