[논문 리뷰] Unifying Map and Landmark Based Representations for Visual Navigation

Saurabh Gupta, David F. Fouhey외 2명|arXiv (Cornell University)|2017. 12. 21.

Robotics and Sensor-Based Localization참고 문헌 32인용 수 64

한 줄 요약

이 논문은 희박한 관측과 노이즈가 있는 작동에도 견고하게 탐색하기 위해 map-based planning과 landmark-based execution을 결합하는 미분가능한 엔드-투-엔드 학습 프레임워크를 제시한다.

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.

연구 동기 및 목표

• 지도 기반 계획과 랜드마크 기반 실행 모두를 활용해 노이즈가 있는 작동을 처리하는 내비게이션 동기를 제시한다.
• 희박하게 등록된 뷰들로부터 공간 표현을 구성하는 학습 가능한 파이프라인을 제안한다.
• 경로를 출력하는 경로 계획자와 경로를 따라 랜드마크를 생성하는 특징 합성기를 개발한다.
• 합성된 특징을 이용해 계획을 따르는 폐루프 제어기를 도입하여 드리프트를 보정한다.

제안 방법

• Map generation: transform sparse registered images into an allocentric spatial map using an egocentric-to-allocentric transformation and dense fusion.
• Path planning: learn a value-iteration-based planner over the learned map to produce a path and corresponding action sequence.
• Path signatures: synthesize features for locations along the path from neighboring views to create a robust path descriptor.
• Plan execution: train a recurrent policy that consumes path signatures and current observation to execute the plan under actuation noise.
• Feature synthesis: fuse representations from multiple reference images weighted by relative pose to approximate features at unseen locations.

실험 결과

연구 질문

• RQ1 Can a learned map from sparse views support reliable path planning and shortcut discovery?
• RQ2 How well can the system synthesize features for unseen locations to support localization and drift correction?
• RQ3 Does incorporating path signatures improve robustness of plan execution under actuation noise?
• RQ4 How does the joint mapper-planner and path-signature execution compare to baselines with open-loop or non-synthesized features?

주요 결과

• Joint mapper and planner can generate meaningful paths from sparse environmental views.
• Feature synthesis outperforms traditional SIFT-based baselines for predicting location-sensitive features.
• Path signatures enable robust plan execution under noise without explicit relocalization or replanning.
• Learned architectures for memory and control outperform standard memory-based networks on navigation tasks in simulated real-world office reconstructions.