Deep Reinforcement Learning for Visual Navigation and Active Tracking

In this contribution, we present our research line on Deep Reinforcement Learning approaches for robot navigation, in particular: Target-Driven Visual Navigation and Visual Active Tracking. We assess our methods capabilities in several challenging scenarios and in a number of environments previously unseen during training. Finally, we also prove that they can be effectively deployed in real-world settings on real platforms.

https://youtu.be/yuFUo1gYGsU

Keywords

Robot Navigation, Learning for Robotics, Computer Vision for Robotics

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average