AI Paper Atlas

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

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Jianhua Han, Meng Tian, Jiangtong Zhu, Fan He, Huixin Zhang, Sitong Guo, Dechang Zhu, Hao Tang, Pei Xu, Yuze Guo, Minzhe Niu, Haojie Zhu and 7 more

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 10 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 IoU confidence trained on real model-prediction distribution (ablation)Percept-WAM 2D detection · nuImages valAP: 48.1 -> 49.6Improved
add IoU confidence trained on random-perturbed GT boxes (ablation)Percept-WAM 2D detection · nuImages valAP: 48.1 -> 46.9Hurt
add IoU confidence trained on uniformly sampled model predictions (ablation)Percept-WAM 2D detection · nuImages valAP: 48.1 -> 46.2Hurt
initialize World-BEV tokens from pretrained LiDAR encoder (ablation)Percept-WAM camera baseline · nuScenes val BEV 3D detectionmAP: 25.0 -> 33.2Improved
add LiDAR and image data augmentation (ablation)Percept-WAM BEV detection · nuScenes valmAP: 33.2 -> 41.3Improved
increase BEV grid resolution from 20x20 to 40x40 (ablation)Percept-WAM BEV detection · nuScenes valmAP: 41.3 -> 50.4Improved
replace AR coordinate decoding with parallel MLP decoding (ablation)Percept-WAM BEV detection · nuScenes valmAP / NDS: mAP 50.4 -> 50.4; NDS 46.6 -> 43.7Mixed
replace AR trajectory decoding with query-based decoding (ablation)Percept-WAM · nuScenes valavg L2 / latency: L2 0.3970 -> 0.3822; latency 2700 -> 1174 msImproved
add streaming inference to query-based decoding (ablation)Percept-WAM · nuScenes vallatency: 1174 -> 707 msImproved
add streaming inference to AR decoding (ablation)Percept-WAM · nuScenes valavg L2: 0.3970 -> 0.4058Hurt
joint training on AD and general datasets vs AD only (ablation)Percept-WAM · nuImages 2D detectionmAP: 49.9 -> 49.6No clear effect
train on all PV tasks (2D + 3D) vs 2D AD only (ablation)Percept-WAM · nuImages 2D detectionmAP: 46.7 -> 49.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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