IEEE Robotics and Automation Letters · 2022 · 29 citations · 23 references
EngineeringComputer ScienceRobotics EngineeringComputer VisionRobot VisionRoboticsActive VisionReinforcement LearningRobotic VisionVisual TrackingActive ExplorationActive Visual ExplorationControl ActionsExplorationReinforcement Learning For VisionScene ExplorationVisual ExplorationVisual Object Tracking
The development of visual tracking systems is becoming a major goal for the Robotics community. Most of the works dealing with this topic focus exclusively on passive tracking, where the target is confined within the camera’s field of view. Only a minority propose active approaches, capable not only of identifying the object to be tracked but also of producing motion control actions to maintain visual contact with it. However, all the methods introduced so far assume that the target is initially in the immediate proximity of the tracker. This represents an undesirable constraint on the applicability of these techniques, and it is to overcome this limitation that we propose a novel End-to-End Deep Reinforcement Learning based system, capable of both exploring the surrounding environment to find the target and then of tracking it. To do this, we develop a network consisting of two sub-components: i) the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Target-Detection Network</i> , which detects the target in the camera’s <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">field-of-view</i> , and ii) the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exploration and Tracking Network</i> , which employs this information to switch between the exploration policy and the tracking policy with the goal of exploring the environment, finding the target and finally tracking it. Through different experiments, we demonstrate the effectiveness of our approach and its superior performance with respect to current state-of-the-art (SotA) methods.
23
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Sebastian Thrun · Communications of the ACM · 2002 · 8K citations
Domain randomization for transferring deep neural networks from simulation to the real world
Josh Tobin, Rachel Fong, Alex Ray et al. · 2017 · 2.8K citations
A frontier-based approach for autonomous exploration
Brian Yamauchi · 2002 · 1.6K citations