AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

ASSISTER: Assistive Navigation via Conditional Instruction Generation

Zanming Huang, Zhongkai Shangguan, Jimuyang Zhang, Gilad Bar, Matthew Boyd, Eshed Ohn-Bar

ECCV 2022 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 15 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 command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-Sim (training conditions)CIDEr: 16.97 -> 23.58Improved
add command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-Sim (new town)CIDEr: 14.49 -> 19.93Improved
add command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-Sim (new town and weather)CIDEr: 11.16 -> 19.61Improved
add command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-SimSPICE: 23.98 -> 26.31 (training), 18.69 -> 18.63 (new town)Mixed
add command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-Real (cross-subject)CIDEr: 10.42 -> 10.74No clear effect
add command-conditional module to goal-only model (ablation)ASSISTER · UrbanWalk-Sim (training conditions)BLEU-4: 10.58 -> 15.49Improved
test on new town instead of training conditions (ablation)ASSISTER (Goal+Command) · UrbanWalk-SimCIDEr: 23.58 -> 19.93Hurt
test on new town and unseen weather instead of new town only (ablation)ASSISTER (Goal+Command) · UrbanWalk-SimCIDEr: 19.93 -> 19.61Hurt
evaluate on real-world data instead of simulationASSISTER (Goal+Command) · UrbanWalkCIDEr: 23.58 -> 10.74Hurt
use ASSISTER instructions instead of Xu et al. baselinehuman followers in blind simulation · Task-based evaluationsuccess rate: 9.52 -> 38.1Improved
use ASSISTER instructions instead of Xu et al. baselinehuman followers in blind simulation · Task-based evaluationroute completion: 46.3 -> 74.1Improved
use ASSISTER instructions instead of Xu et al. baselinehuman followers in blind simulation · Task-based evaluationcollision with static obstacles: 6.0 -> 14.0Hurt

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