Grounding Driving VLA via Inverse Kinematics

• URL: http://arxiv.org/abs/2605.21061v1
• Date: Wed, 20 May 2026 11:45:32 GMT
• Title: Grounding Driving VLA via Inverse Kinematics
• Abstract summary: We show that trajectory recovery requires both a current and a future visual state as boundary conditions.<n>We re-design Driving VLA in the style of an inverse kinematics solver.<n>With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs.
• Score: 32.65844881404964
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.

Related papers

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving [66.93548079427477]
  We present SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal.<n>An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without explicit future-frame generation at inference.<n>Our SimWAM achieves 91.5 PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes.
  arXiv  Detail & Related papers  (2026-08-07T17:59:09Z)
• Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning [32.59795755994378]
  We introduce inverse dynamics learning as an auxiliary objective that directly supervises the Vision-Language-Action (VLA) vision encoder.<n>By predicting the action between current and future observations, our objective encourages the encoder to capture fine-grained visual distinctions that determine low-level actions.<n> Experiments on CALVIN ABC-D and SimplerEnv show consistent gains across diverse VLA baselines.
  arXiv  Detail & Related papers  (2026-05-28T08:22:49Z)
• LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model [16.87741001074065]
  Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving.<n>Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction.<n>We propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving.
  arXiv  Detail & Related papers  (2026-05-21T07:31:49Z)
• MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving [54.57163800903507]
  We present MindVLA-U1, the first unified streaming VLA architecture for autonomous driving.<n>A unified VLM backbone produces AR language tokens and flow-matching continuous action trajectories in a single forward pass over one shared representation.<n>On the long-tail WOD-E2E benchmark, MindVLA-U1 surpasses experienced human drivers for the first time.
  arXiv  Detail & Related papers  (2026-05-12T18:09:42Z)
• FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving [20.991905328262746]
  We introduce a novel ego-scene interactive modeling paradigm.<n>Inspired by human recognition, the paradigm represents ego-scene interaction as the scene flow relative to the ego-vehicle.<n>Within it, an ego-guided scene partition first constructs basic flow units to quantify scene flow.<n>Then, based on flow units, spatial and temporal flow predictions are performed to model dynamics of scene flow.
  arXiv  Detail & Related papers  (2026-03-11T16:28:53Z)
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model [73.03346643967309]
  We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling.<n>FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information.<n>In the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors.
  arXiv  Detail & Related papers  (2026-03-11T12:39:55Z)
• ReViP: Reducing False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance [50.05984919728878]
  We present ReViP, a novel VLA framework with Vision-Proprioception Rebalance to enhance visual grounding and robustness under perturbations.<n>Specifically, we use an external VLM as a task-stage observer to extract real-time task-centric visual cues from visual observations.<n>To evaluate false completion, we propose the first False-Completion Benchmark Suite built on LIBERO with controlled settings such as Object-Drop.
  arXiv  Detail & Related papers  (2026-01-23T11:31:07Z)
• Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution [96.25314747309811]
  We introduce SeerDrive, a novel end-to-end framework that jointly models future scene evolution and trajectory planning.<n>Our method first predicts future bird's-eye view (BEV) representations to anticipate the dynamics of the surrounding scene.<n>Two key components enable this: (1) future-aware planning, which injects predicted BEV features into the trajectory planner, and (2) iterative scene modeling and vehicle planning.
  arXiv  Detail & Related papers  (2025-10-13T07:41:47Z)
• FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning [75.80110543049783]
  We propose FastDriveVLA, a reconstruction-based vision token pruning framework for autonomous driving.<n>A novel foreground adversarial-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models.<n>Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.
  arXiv  Detail & Related papers  (2025-07-31T07:55:56Z)
• LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints [16.861461971702596]
  Trajectory prediction for autonomous driving must continuously reason the motionity of road agents and comply with scene constraints. Existing methods typically rely on one-stage trajectory prediction models, which condition future trajectories on observed trajectories combined with fused scene information. We present a novel method, called LAformer, which uses a temporally dense lane-aware estimation module to select only the top highly potential lane segments in an HD map.
  arXiv  Detail & Related papers  (2023-02-27T16:34:16Z)
• Monocular BEV Perception of Road Scenes via Front-to-Top View Projection [57.19891435386843]
  We present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view. Our model runs at 25 FPS on a single GPU, which is efficient and applicable for real-time panorama HD map reconstruction.
  arXiv  Detail & Related papers  (2022-11-15T13:52:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.