M
Mukunda Bharatheesha
Researcher at Delft University of Technology
Publications - 13
Citations - 296
Mukunda Bharatheesha is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Motion planning & Robot. The author has an hindex of 6, co-authored 12 publications receiving 244 citations.
Papers
More filters
Book ChapterDOI
Team Delft’s robot winner of the Amazon Picking Challenge 2016
Carlos Hernández,Mukunda Bharatheesha,Wilson Ko,Hans Gaiser,Jethro Tan,Kanter van Deurzen,Maarten de Vries,Bas Van Mil,Jeff van Egmond,Ruben Burger,Mihai Morariu,Jihong Ju,Xander Gerrmann,Ronald Ensing,Jan van Frankenhuyzen,Martijn Wisse +15 more
TL;DR: The robot’s software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning.
Journal ArticleDOI
Integrating Different Levels of Automation: Lessons From Winning the Amazon Robotics Challenge 2016
TL;DR: This paper proposes automation levels based on the usage of information at design or runtime to drive the robot's behavior, and uses them to discuss Team Delft's design solution and the lessons learned from this robot development experience.
Posted Content
Team Delft's Robot Winner of the Amazon Picking Challenge 2016
Carlos Hernández,Mukunda Bharatheesha,Wilson Ko,Hans Gaiser,Jethro Tan,Kanter van Deurzen,Maarten de Vries,Bas Van Mil,Jeff van Egmond,Ruben Burger,Mihai Morariu,Jihong Ju,Xander Gerrmann,Ronald Ensing,Jan van Frankenhuyzen,Martijn Wisse +15 more
TL;DR: The winning team of Team Delft as mentioned in this paper used an industrial robot arm, 3D cameras and a customized gripper for picking and placing items in an Amazon warehouse, which won both the picking and the stowing tasks.
Proceedings ArticleDOI
Distance metric approximation for state-space RRTs using supervised learning
TL;DR: This work uses the Iterative Linear Quadratic Regulator approach for estimating an approximation to the optimal cost and learns this cost using Locally Weighted Projection Regression and shows that the learnt function approximates the original cost with a reasonable tolerance and gives a tremendous speed up of a factor of 1000 over the actual computation time.
Journal ArticleDOI
RRT-CoLearn: Towards Kinodynamic Planning Without Numerical Trajectory Optimization
TL;DR: In this article, the authors proposed to use indirect optimal control instead of direct optimal control to reduce the computational effort to generate the data and provide a low-dimensional parametrization of the action space.