Target Driven Visual Navigation

Visual navigation is a core problem in robotics and machine vision. Previous research used map-based, map-building or map-less navigation strategies. The first two approaches were favored in the past, however, they essentially depend on the accurate mapping of the environment and a careful human-guided training phase, which overall limits generalizability. With recent developments in Deep Reinforcement Learning (DRL), map-less navigation experienced major advancements. A current challenge for DRL algorithms is learning new tasks or goals. This ability is called transfer learning. To cope with the challenges in transfer learning and performance, we present a novel approach, using Universal Successor Features (USF). We propose several models that we applied for the task of target driven visual navigation in a complex photo-realistic environment using a simulator named as AI2THOR. With the evaluation of our proposed models in AI2THOR, we demonstrate that an agent is able to improve the Transfer Reinforcement Learning ability.

Publications

  • Siriwardhana, S., Weerasekera, R. and Nanayakkara, S. (2018). Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations. Deep RL Workshop NeurIPS 2018. [PDF] [URL]