What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies

• URL: http://arxiv.org/abs/2609.05376v1
• Date: Fri, 04 Sep 2026 17:27:35 GMT
• Title: What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies
• Abstract summary: Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects are introduced.<n>We introduce distractor objects with controlled color and shape similarity and localize failures to picking and placement.<n>We find that distractor sensitivity is specific to both the type of visual similarity and the manipulation stage.
• Score: 28.136436759581926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a problem of conditional visual grounding: the visual target required for successful control changes with the manipulation phase and, in more complex tasks, with the observed task state. Using Action Chunking with Transformers (ACT), we systematically introduce distractor objects and receptacles with controlled color and shape similarity and localize failures to picking and placement. We find that distractor sensitivity is specific to both the type of visual similarity and the manipulation stage. Guided by this diagnosis, we evaluate distractor augmentation, phase-dependent attention regularization, and appearance-based visual prompting as complementary interventions for improving target selection while preserving spatial information required for control. These interventions substantially improve robustness in simulation and on a physical UR3e. We further examine the same failure pattern in a pretrained vision-language-action policy on a state-conditioned instrument-handling task, where the observed state of a medical instrument determines the correct destination. Together, the results show that visual distractors can cause incorrect object or destination selection even when the underlying manipulation skill remains intact, and that explicitly improving target selection can substantially recover performance across distinct visuomotor policy-learning regimes.

Related papers

• Rethinking Generic Object Tracking Toward Human-Level Perceptual Intelligence [0.8883733362171032]
  The dissertation aims to narrow the gap between machine visual tracking systems and human visual perception.<n>It proposes a series of methods that systematically enhance the target discrimination, robust adaptation, and geometric reasoning capabilities of tracking models.
  arXiv  Detail & Related papers  (2026-07-01T18:54:00Z)
• MSACT: Multistage Spatial Alignment for Stable Low-Latency Fine Manipulation [4.439585594082787]
  Real-world fine manipulation, particularly in bimanual manipulation, requires low-latency control and stable visual localization.<n>Existing approaches make different trade-offs: action-chunking policies such as ACT enable low-latency execution and data efficiency but rely on dense visual features without explicit spatial consistency.<n>We introduce a multistage spatial attention module that extracts stable 2D attention points and jointly predicts future attention sequences with a temporal alignment loss.
  arXiv  Detail & Related papers  (2026-05-01T07:35:15Z)
• When would Vision-Proprioception Policies Fail in Robotic Manipulation? [24.653339846980376]
  Proprioceptive information is critical for precise servo control by providing real-time robotic states.<n>Recent studies have reported inconsistent observations on the generalization of vision-proprioception policies.<n>We propose the Gradient Adjustment with Phase-guidance (GAP) algorithm that adaptively modulates the optimization of proprioception.
  arXiv  Detail & Related papers  (2026-02-12T15:00:48Z)
• \ extsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• 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)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues [69.24378760740171]
  We address visuomotor policy feature pooling as a solution to the observed lack of robustness in perturbed scenes.<n>We achieve this via Attentive Feature Aggregation (AFA), a lightweight, trainable pooling mechanism that learns to naturally attend to task-relevant visual cues.<n>Our findings show that ignoring extraneous visual information is a crucial step towards deploying robust and generalisable visuomotor policies.
  arXiv  Detail & Related papers  (2025-11-13T19:31:05Z)
• Exploring Conditions for Diffusion models in Robotic Control [70.27711404291573]
  We explore leveraging pre-trained text-to-image diffusion models to obtain task-adaptive visual representations for robotic control.<n>We find that naively applying textual conditions yields minimal or even negative gains in control tasks.<n>We propose ORCA, which introduces learnable task prompts that adapt to the control environment and visual prompts that capture fine-grained, frame-specific details.
  arXiv  Detail & Related papers  (2025-10-17T10:24:14Z)
• Top-Down Visual Attention from Analysis by Synthesis [87.47527557366593]
  We consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. We propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and controllable achieves top-down attention.
  arXiv  Detail & Related papers  (2023-03-23T05:17:05Z)
• Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation [26.47544415550067]
  We propose to distill a state-based motion planner augmented policy to a visual control policy. We evaluate our method on three manipulation tasks in obstructed environments. Our framework is highly sample-efficient and outperforms the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-11-11T18:52:00Z)

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.