arXiv:2510.08562v2 Announce Type: replace 
Abstract: End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal imbalance of trajectory data. This imbalance creates a significant optimization burden, causing models to learn spurious correlations instead of robust driving logic, while also prioritizing uncertain, distant predictions, thereby compromising immediate safety. To address these issues, we propose ResAD, a novel Normalized Residual Trajectory Modeling framework. Instead of predicting the future trajectory directly, our approach reframes and simplifies the learning task by predicting the residual deviation from a deterministic inertial reference. This inertial reference serves as a strong physical prior, compelling the model to move beyond simple pattern-matching and instead focus its capacity on learning the necessary, context-driven deviations (e.g., traffic rules, obstacles) from this default, inertially-guided path. To mitigate the optimization imbalance caused by uncertain, long-term horizons, ResAD further incorporates Point-wise Normalization of the predicted residual. This technique re-weights the optimization objective, preventing large-magnitude errors associated with distant, uncertain waypoints from dominating the learning signal. On the NAVSIM v1 and v2 benchmarks, ResAD achieves state-of-the-art results of 88.8 PDMS and 85.5 EPDMS with only two denoising steps, demonstrating that ResAD significantly simplifies the learning task and improves planning performance. The code will be released to facilitate further research.

تم تقديم إطار جديد يسمى ResAD لتحسين أنظمة القيادة الذاتية من النهاية إلى النهاية من خلال معالجة التحديات التي تطرحها عدم التوازن الزماني والمكاني في بيانات المسار. يركز هذا النهج على التنبؤ بالانحراف المتبقي عن مرجع قصوري محدد بدلاً من التنبؤ المباشر بالمسارات المستقبلية، بهدف تحسين متانة النموذج والسلامة الفورية.

Se ha introducido un nuevo marco llamado ResAD para mejorar los sistemas de conducción autónoma de extremo a extremo, abordando los desafíos que presentan los desequilibrios espaciotemporales en los datos de trayectoria. Este enfoque se centra en predecir la desviación residual de una referencia inercial determinista en lugar de prever directamente las trayectorias futuras, con el objetivo de mejorar la robustez del modelo y la seguridad inmediata.

Un nouveau cadre nommé ResAD a été introduit pour améliorer les systèmes de conduite autonome de bout en bout en s'attaquant aux défis posés par les déséquilibres spatio-temporels dans les données de trajectoire. Cette approche se concentre sur la prédiction de la déviation résiduelle par rapport à une référence inertielle déterministe plutôt que de prévoir directement les trajectoires futures, dans le but d'améliorer la robustesse du modèle et la sécurité immédiate.

A novel framework named ResAD has been introduced to enhance end-to-end autonomous driving systems by addressing the challenges posed by spatio-temporal imbalances in trajectory data. This approach focuses on predicting the residual deviation from a deterministic inertial reference rather than directly forecasting future trajectories, aiming to improve model robustness and immediate safety.

ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving

arXiv:2511.19221v1 Announce Type: new 
Abstract: Autonomous driving heavily relies on accurate and robust spatial perception. Many failures arise from inaccuracies and instability, especially in long-tail scenarios and complex interactions. However, current vision-language models are weak at spatial grounding and understanding, and VLA systems built on them therefore show limited perception and localization ability. To address these challenges, we introduce Percept-WAM, a perception-enhanced World-Awareness-Action Model that is the first to implicitly integrate 2D/3D scene understanding abilities within a single vision-language model (VLM). Instead of relying on QA-style spatial reasoning, Percept-WAM unifies 2D/3D perception tasks into World-PV and World-BEV tokens, which encode both spatial coordinates and confidence. We propose a grid-conditioned prediction mechanism for dense object perception, incorporating IoU-aware scoring and parallel autoregressive decoding, improving stability in long-tail, far-range, and small-object scenarios. Additionally, Percept-WAM leverages pretrained VLM parameters to retain general intelligence (e.g., logical reasoning) and can output perception results and trajectory control outputs directly. Experiments show that Percept-WAM matches or surpasses classical detectors and segmenters on downstream perception benchmarks, achieving 51.7/58.9 mAP on COCO 2D detection and nuScenes BEV 3D detection. When integrated with trajectory decoders, it further improves planning performance on nuScenes and NAVSIM, e.g., surpassing DiffusionDrive by 2.1 in PMDS on NAVSIM. Qualitative results further highlight its strong open-vocabulary and long-tail generalization.

يمثل تقديم Percept-WAM تقدمًا كبيرًا في تكنولوجيا القيادة الذاتية، حيث يركز على تحسين الإدراك المكاني من خلال نموذج موحد للرؤية واللغة يدمج فهم المشاهد ثنائية وثلاثية الأبعاد. يعالج هذا النموذج قيود الأنظمة الحالية، التي غالبًا ما تواجه صعوبات في الدقة والثبات في سيناريوهات القيادة المعقدة.

La introducción de Percept-WAM marca un avance significativo en la tecnología de conducción autónoma, centrándose en mejorar la percepción espacial a través de un modelo de visión-lenguaje unificado que integra la comprensión de escenas en 2D y 3D. Este modelo aborda las limitaciones de los sistemas existentes, que a menudo luchan con la precisión y la estabilidad en escenarios de conducción complejos.

L'introduction de Percept-WAM représente une avancée significative dans la technologie de conduite autonome, en se concentrant sur l'amélioration de la perception spatiale grâce à un modèle de vision-langage unifié qui intègre la compréhension des scènes en 2D et 3D. Ce modèle répond aux limitations des systèmes existants, qui ont souvent du mal avec l'exactitude et la stabilité dans des scénarios de conduite complexes.

The introduction of Percept-WAM marks a significant advancement in autonomous driving technology, focusing on enhancing spatial perception through a unified vision-language model that integrates 2D and 3D scene understanding. This model addresses the limitations of existing systems, which often struggle with accuracy and stability in complex driving scenarios.

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

arXiv:2506.06659v3 Announce Type: replace-cross 
Abstract: Autonomous vehicles must navigate safely in complex driving environments. Imitating a single expert trajectory, as in regression-based approaches, usually does not explicitly assess the safety of the predicted trajectory. Selection-based methods address this by generating and scoring multiple trajectory candidates and predicting the safety score for each. However, they face optimization challenges in precisely selecting the best option from thousands of candidates and distinguishing subtle but safety-critical differences, especially in rare and challenging scenarios. We propose DriveSuprim to overcome these challenges and advance the selection-based paradigm through a coarse-to-fine paradigm for progressive candidate filtering, a rotation-based augmentation method to improve robustness in out-of-distribution scenarios, and a self-distillation framework to stabilize training. DriveSuprim achieves state-of-the-art performance, reaching 93.5% PDMS in NAVSIM v1 and 87.1% EPDMS in NAVSIM v2 without extra data, with 83.02 Driving Score and 60.00 Success Rate on the Bench2Drive benchmark, demonstrating superior planning capabilities in various driving scenarios.

تم تقديم DriveSuprim كنهج جديد لتحسين اختيار المسارات للمركبات المستقلة، حيث يتناول التحديات المتعلقة بالتنقل بأمان في بيئات القيادة المعقدة. تستخدم هذه الطريقة نموذجًا من الخشن إلى الدقيق لتصفية المرشحين وتدمج تحسينات قائمة على الدوران لتعزيز المتانة في السيناريوهات النادرة.

DriveSuprim se ha presentado como un enfoque novedoso para mejorar la selección de trayectorias para vehículos autónomos, abordando los desafíos de navegar de manera segura en entornos de conducción complejos. Este método emplea un paradigma de filtrado de candidatos de grueso a fino e incorpora una augmentación basada en rotación para mejorar la robustez en escenarios raros.

DriveSuprim a été introduit comme une nouvelle approche pour améliorer la sélection de trajectoires pour les véhicules autonomes, abordant les défis de la navigation en toute sécurité dans des environnements de conduite complexes. Cette méthode utilise un paradigme grossier à fin pour le filtrage des candidats et intègre une augmentation basée sur la rotation pour améliorer la robustesse dans des scénarios rares.

DriveSuprim has been introduced as a novel approach to enhance trajectory selection for autonomous vehicles, addressing the challenges of safely navigating complex driving environments. This method employs a coarse-to-fine paradigm for candidate filtering and incorporates rotation-based augmentation to improve robustness in rare scenarios.

ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving

Was this article worth reading? Share it

Dyad

Alternative to jobscan

LucidQuery AI