Learning to Navigate in Complex Environments
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and task performance can be dramatically improved by relying on additional auxiliary tasks leveraging multimodal sensory inputs. In particular we consider jointly learning the goal-driven reinforcement learning problem with auxiliary depth prediction and loop closure classification tasks. This approach can learn to navigate from raw sensory input in complicated 3D mazes, approaching human-level performance even under conditions where the goal location changes frequently. We provide detailed analysis of the agent behaviour, its ability to localise, and its network activity dynamics, showing that the agent implicitly learns key navigation abilities.
Code (1)
Tasks
Depth EstimationDepth PredictionGeneral ClassificationNavigatereinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Autonomous Port Navigation With Ranging Sensors Using Model-Based Reinforcement Learning
Autonomous shipping has recently gained much interest in the research community. However, little research focuses on inland - and port navigation, even though this is identified by countries such as Belgium and the Nethe…
Model-based Reinforcement LearningNavigatereinforcement-learningReinforcement LearningBio-Inspired Hybrid Map: Spatial Implicit Local Frames and Topological Map for Mobile Cobot Navigation
Navigation is a fundamental capacity for mobile robots, enabling them to operate autonomously in complex and dynamic environments. Conventional approaches use probabilistic models to localize robots and build maps simult…
Reinforcement LearningGrid Cells, Border Cells and Discrete Complex Analysis
We propose a mechanism enabling the appearance of border cells -- neurons firing at the boundaries of the navigated enclosures. The approach is based on the recent discovery of discrete complex analysis on a triangular l…
Learning to Visually Navigate in Photorealistic Environments Without any Supervision
Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it difficult to provide supervision during traini…
NavigatePositionAdaVLN: Towards Visual Language Navigation in Continuous Indoor Environments with Moving Humans
Visual Language Navigation is a task that challenges robots to navigate in realistic environments based on natural language instructions. While previous research has largely focused on static settings, real-world navigat…
Navigate