Sensor fusion for robot control through deep reinforcement learning
Sensor fusion for robot control through deep reinforcement learning
复制标题
DOI：
10.1109/iros.2017.8206048
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Steven Bohez;Tim Verbelen;E. D. Coninck;B. Vankeirsbilck;P. Simoens;B. Dhoedt
中科院分区：
文献类型：
--
作者：
Steven Bohez;Tim Verbelen;E. D. Coninck;B. Vankeirsbilck;P. Simoens;B. Dhoedt
深度强化学习在机器人控制算法中变得越来越流行，其目的是让机器人从非结构化的感官输入中自学习有用的特征表示，从而形成最佳的驱动策略。除了安装在机器人上的传感器之外，传感器也可能部署在环境中，尽管这些传感器可能需要通过不可靠的无线连接进行访问。在本文中，我们演示了深度神经网络架构，该架构能够融合多个传感器生成的信息，并且对运行时的传感器故障具有鲁棒性。我们在模拟和现实世界中评估机器人搜索和挑选任务的方法。
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information generated by multiple sensors and are robust to sensor failures at runtime. We evaluate our method on a search and pick task for a robot both in simulation and the real world.