Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours
Current model free learning-based robot grasping approaches exploit human-labeled
datasets for training the models. However, there are two problems with such a …
datasets for training the models. However, there are two problems with such a …
A survey of motion planning and related geometric algorithms
JT Schwartz, M Sharir - Artificial Intelligence, 1988 - Elsevier
This paper surveys recent developments in motion planning and related geometric
algorithms, a theoretical research area that has grown rapidly in response to increasing …
algorithms, a theoretical research area that has grown rapidly in response to increasing …
Learning to manipulate deformable objects without demonstrations
In this paper we tackle the problem of deformable object manipulation through model-free
visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we …
visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we …
[图书][B] Simulating humans: computer graphics animation and control
During the past decade, high-performance computer graphics have found application in an
exciting and expanding range of new domains. Among the most dramatic developments has …
exciting and expanding range of new domains. Among the most dramatic developments has …
The curious robot: Learning visual representations via physical interactions
What is the right supervisory signal to train visual representations? Current approaches in
computer vision use category labels from datasets such as ImageNet to train ConvNets …
computer vision use category labels from datasets such as ImageNet to train ConvNets …
A simple motion-planning algorithm for general robot manipulators
T Lozano-Perez - IEEE Journal on Robotics and Automation, 1987 - ieeexplore.ieee.org
A simple and efficient algorithm is presented, using configuration space, to plan collision-
free motions for general manipulators. An implementation of the algorithm for manipulators …
free motions for general manipulators. An implementation of the algorithm for manipulators …
Learning to push by grasping: Using multiple tasks for effective learning
Recently, end-to-end learning frameworks are gaining prevalence in the field of robot
control. These frameworks input states/images and directly predict the torques or the action …
control. These frameworks input states/images and directly predict the torques or the action …
Artificial intelligence and robotics
M Brady - Artificial intelligence, 1985 - Elsevier
Since Robotics is the field concerned with the connection of perception to action, Artificial
Intelligence must have a central role in Robotics if the connection is to be intelligent. Artificial …
Intelligence must have a central role in Robotics if the connection is to be intelligent. Artificial …
Computer animation of knowledge-based human grasping
H Rijpkema, M Girard - ACM Siggraph Computer Graphics, 1991 - dl.acm.org
The synthesis of human hand motion and grasping of arbitrary shaped objects is a very
complex problem. Therefore high-level control is needed to perform these actions. In order …
complex problem. Therefore high-level control is needed to perform these actions. In order …
Avoiding obstacles and resolving kinematic redundancy
J Baillieul - … . 1986 IEEE International Conference on Robotics …, 1986 - ieeexplore.ieee.org
While obstacles in a robot workspace can effectively reduce the number of degrees of
freedom, there need not be a corresponding loss of functionality for kinematically redundant …
freedom, there need not be a corresponding loss of functionality for kinematically redundant …