Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots
This work addresses the challenge of object searching for mobile robots, which is more difficult than scene finding due to small object sizes and arbitrary poses, representing an incremental improvement in robotics navigation.
The authors tackled the problem of learning a navigation policy for robots to actively search for small, arbitrarily posed objects in indoor environments using only visual inputs, and their method outperformed competing methods in average trajectory length and success rate in both simulation and real-world experiments.
We study the problem of learning a navigation policy for a robot to actively search for an object of interest in an indoor environment solely from its visual inputs. While scene-driven visual navigation has been widely studied, prior efforts on learning navigation policies for robots to find objects are limited. The problem is often more challenging than target scene finding as the target objects can be very small in the view and can be in an arbitrary pose. We approach the problem from an active perceiver perspective, and propose a novel framework that integrates a deep neural network based object recognition module and a deep reinforcement learning based action prediction mechanism. To validate our method, we conduct experiments on both a simulation dataset (AI2-THOR) and a real-world environment with a physical robot. We further propose a new decaying reward function to learn the control policy specific to the object searching task. Experimental results validate the efficacy of our method, which outperforms competing methods in both average trajectory length and success rate.