AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Visual Memory for Robust Path Following

Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 30 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use RPF instead of open-loop replaypath following · SBPD area4Success Rate: 0.216 -> 0.866Improved
Use RPF instead of 3D reconstruction and localizationpath following · SBPD area4Success Rate: 0.826 -> 0.866Improved
Add visual features to the path memory (ablation)RPF · SBPD area4, FollowingSuccess Rate: 0.782 -> 0.866Improved
Add visual features to the path memory (ablation)RPF · SBPD area4, HomingSuccess Rate: 0.780 -> 0.866Improved
Use RPF instead of 3D reconstruction and localizationhoming · SBPD area4Success Rate: 0.000 -> 0.866Improved
Replace the recurrent controller with a feed-forward network (ablation)RPF · path retracingSuccess RateHurt
Replace the learned pointer increment with a constant increment (ablation)RPF · path retracingSuccess RateHurt
Use a standard GRU without the proposed sequential memory (ablation)path retracing · path retracingSuccess RateHurt
Use trained nearest-neighbor action votingpath retracing · path retracingSuccess RateHurt
Increase path length beyond the training lengthRPF · novel environmentsSuccess Rate: 3×Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy