Unifying Map and Landmark Based Representations for Visual Navigation

Abstract

This works presents a formulation for visual navigation that unifies map based spatial reasoning and path planning, with landmark based robust plan execution in noisy environments. Our proposed formulation is learned from data and is thus able to leverage statistical regularities of the world. This allows it to efficiently navigate in novel environments given only a sparse set of registered images as input for building representations for space. Our formulation is based on three key ideas: a learned path planner that outputs path plans to reach the goal, a feature synthesis engine that predicts features for locations along the planned path, and a learned goal-driven closed loop controller that can follow plans given these synthesized features. We test our approach for goal-driven navigation in simulated real world environments and report performance gains over competitive baseline approaches.

Project page with videos: https://s-gupta.github.io/cmpl/

References in corpus (4)

• Learning to Navigate in Complex Environments
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Neural Map: Structured Memory for Deep Reinforcement Learning
• Learning Transferable Policies for Monocular Reactive MAV Control

Cited by in corpus (12)

• Emergence of Exploratory Look-Around Behaviors through Active Observation Completion
• Causal Navigation by Continuous-time Neural Networks
• A Behavioral Approach to Visual Navigation with Graph Localization Networks
• Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
• Learning to Navigate in Indoor Environments: from Memorizing to Reasoning
• Topological Planning with Transformers for Vision-and-Language Navigation
• Graph Attention Memory for Visual Navigation
• MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation
• SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
• MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
• Deep Visual MPC-Policy Learning for Navigation
• Learning Autonomous Exploration and Mapping with Semantic Vision