抓住
夹持器
强化学习
人工智能
计算机科学
机器人
动作(物理)
人机交互
具身认知
规划师
认知机器人学
仿人机器人
软机器人
工程类
演示式编程
机械臂
机器人学习
机器人学
控制(管理)
进化机器人
任务分析
机械设计
深度学习
主动学习(机器学习)
软质材料
控制工程
作者
Enrico Turco,Valerio Bo,Chiara Castellani,Gionata Salvietti,Monica Malvezzi,Domenico Prattichizzo,María Pozzi
出处
期刊:IEEE Robotics & Automation Magazine
[Institute of Electrical and Electronics Engineers]
日期:2026-01-12
卷期号:33 (1): 39-51
被引量:1
标识
DOI:10.1109/mra.2025.3639825
摘要
In this work, we investigate how a state-of-the-art grasp planner based on deep reinforcement learning performs when applied to a soft-rigid gripper in a decluttering task. The gripper, called Soft ScoopGripper, is endowed with a rigid scoopshaped part that facilitates the interaction with the environment and with objects. We hypothesize that the clever design of such a gripper can facilitate the learning process, reducing the number of required training steps and eliminating the need for learning non-prehensile actions, such as pushing. To validate our hypothesis, we conducted experiments in both simulated and realworld environments, comparing the selected gripper with a rigid parallel-jaw gripper and a four-fingered soft gripper. Results show that the Soft ScoopGripper learns to effectively declutter scenes using a single action (grasping) instead of two (pushing and grasping). This is due to the fact that the scoop-shaped addon allows to perform non-prehensile motions during the grasp action.
科研通智能强力驱动
Strongly Powered by AbleSci AI