Sensor Fusion for Robot Control through Deep Reinforcement Learning
This work addresses sensor fusion for robot control, which is an incremental improvement for robotics applications using deep reinforcement learning.
The paper tackles the problem of robot control by developing deep neural network architectures that fuse information from multiple sensors and are robust to sensor failures, achieving successful performance in both simulation and real-world search and pick tasks.
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 coming from 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.