Cheong, Sanghun Cho, Brian Y. Lee, Jinhwi Lee, Jeongho Kim, Dong Hwan Nam, Changjoo Kim, Chang-hwan Park, Sung-kee 2024-01-19T14:01:11Z 2024-01-19T14:01:11Z 2022-01-10 2021-09 1861-2776 https://pubs.kist.re.kr/handle/201004/116515 We propose a learning-based method to solve the problem of rearranging objects in clutter to obtain a collision-free path for retrieving a target object by a robotic manipulator. The method provides the solutions for what obstacles to remove and where to place them in what orders to rearrange the obstacles. The proposed method uses a deep Q-network to learn the optimal policies for robot's rearranging actions. To apply the network, it is assumed that the configurations of objects and environment are known and the environment is considered as a grid space. Two types of structures for a deep Q-network are proposed according to action characteristics for this problem. From extensive simulation experiments, we showed that our algorithm could reduce the number of rearranged obstacles and the total execution time significantly (up to 35%) compared to a baseline method. The experiments were performed by a real robot with a vision system and showed the feasibility of the proposed method on real world. English SPRINGER HEIDELBERG Obstacle rearrangement for robotic manipulation in clutter using a deep Q-network Article 10.1007/s11370-021-00377-4 1 INTELLIGENT SERVICE ROBOTICS, v.14, no.4, pp.549 - 561 INTELLIGENT SERVICE ROBOTICS 14 4 549 561 scie scopus 000684063500001 2-s2.0-85112256270 Robotics Robotics Article Object rearrangement Manipulation planning Deep Q-network