Few-experiential learning system of robotic picking task with selective dual-arm grasping
Few-experiential learning system of robotic picking task with selective dual-arm grasping
复制标题
DOI：
10.1080/01691864.2020.1783352
复制
发表时间：
2020-06-23
影响因子：
2
通讯作者：
Inaba, Masayuki
中科院分区：
文献类型：
--
作者：
Kitagawa, Shingo;Wada, Kentaro;Inaba, Masayuki
最近，机器人被引入仓库和工厂以实现自动化，并期望像人类一样执行双臂操作，并操作大型，重型和不平衡的物体。本文针对复杂环境下的目标拾取任务，旨在实现机器人从单臂和双臂运动中选择并执行适当抓取运动的机器人拾取系统。在本文中，我们提出了一个基于少量经验学习的目标拾取系统与选择性双臂抓取。在我们的系统中，机器人首先学习抓取点和对象的语义和实例标签与自动合成的数据集。然后，机器人执行并收集真实的世界中的抓取试验经验，并利用收集的试验经验重新训练抓取点预测模型。最后，机器人评估抓取对象实例、策略和点的候选对，并选择执行最优抓取运动。在实验中，我们评估了我们的系统进行目标拾取任务的实验与双臂人形机器人巴克斯特在仓库的杂乱环境。
Recently, robots are introduced to warehouses and factories for automation and are expected to execute dual-arm manipulation as human does and to manipulate large, heavy and unbalanced objects. We focus on target picking task in the cluttered environment and aim to realize a robot picking system which the robot selects and executes proper grasping motion from single-arm and dual-arm motion. In this paper, we propose a few-experiential learning-based target picking system with selective dual-arm grasping. In our system, a robot first learns grasping points and object semantic and instance label with automatically synthesized dataset. The robot then executes and collects grasp trial experiences in the real world and retrains the grasping point prediction model with the collected trial experiences. Finally, the robot evaluates candidate pairs of grasping object instance, strategy and points and selects to execute the optimal grasping motion. In the experiments, we evaluated our system by conducting target picking task experiments with a dual-arm humanoid robot Baxter in the cluttered environment as warehouse.