AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation

Ruihai Wu, Chuanruo Ning, Hao Dong

ICCV 2023 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 22 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
add state value estimates (foresightful affordance) instead of greedy distance-only supervision (ablation)dense affordance · SoftGym SpreadClothnormalized score: 0.701 -> 0.758Improved
add state value estimates (ablation)dense affordance · SoftGym RopeConfigurationnormalized score: 0.460 -> 0.529Improved
add value-aware stages beyond stage 1 (more stages of data) (ablation)dense affordance · SoftGym SpreadClothnormalized score: 0.589 -> 0.758Improved
use value-aware training at stage 1 versus greedy distance-only (ablation)dense affordance · SoftGym SpreadCloth (stage 1)normalized score: 0.701 -> 0.589Hurt
add Integrated Systematic Training (IST) (ablation)dense affordance · SoftGym SpreadClothnormalized score: 0.612 -> 0.758Improved
add IST (ablation)dense affordance · DeformableRavens cable-ringsuccess rate (%): 78.3 -> 81.7Improved
use learned picking affordance instead of random picking (ablation)dense affordance · DeformableRavens cable-ringsuccess rate (%): 11.7 -> 81.7Improved
use learned picking affordance instead of Transporter expert picking (ablation)dense affordance · DeformableRavens cable-ring-notargetsuccess rate (%): 41.7 -> 95.0Improved
dense affordance learning without expert demonstrations versus Transporter imitationTransporter · DeformableRavens cable-ringsuccess rate (%): 68.3 -> 81.7Improved
supervised dense affordance versus RL baselinesMVP, PlaNet, CURL-SAC, DrQ · SoftGym SpreadClothnormalized score: 0.387 -> 0.758Improved
novel bead counts (generalization) versus TransporterTransporter · cable-ring 24 beadssuccess rate (%): 33.3 -> 61.6Improved
real-world fine-tuned affordance versus MVPMVP · Real world SpreadClothnormalized score: 0.307 -> 0.683Improved

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