AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making
Vision-Language Models (VLMs) encode knowledge and reasoning capabilities for robotic manipulation within high-dimensional representation spaces. However, current approaches often project them into compressed intermediate representations, discarding important task-specific information such as fine-grained spatial or semantic details. To address this, we propose AntiGrounding, a new framework that reverses the instruction grounding process. It lifts candidate actions directly into the VLM representation space, renders trajectories from multiple views, and uses structured visual question answering for instruction-based decision making. This enables zero-shot synthesis of optimal closed-loop robot trajectories for new tasks. We also propose an offline policy refinement module that leverages past experience to enhance long-term performance. Experiments in both simulation and real-world environments show that our method outperforms baselines across diverse robotic manipulation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingQuestion AnsweringVisual Question AnsweringSimilar Papers 제목 키워드 기반
Pre-training Auto-regressive Robotic Models with 4D Representations
Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highlighting the importance of pre-training. Y…
Depth EstimationMonocular Depth EstimationPoint TrackingTransfer LearningLift3D Policy: Lifting 2D Foundation Models for Robust 3D Robotic Manipulation
3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has…
Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has inc…
Multi-Object Grasping -- Estimating the Number of Objects in a Robotic Grasp
A human hand can grasp a desired number of objects at once from a pile based solely on tactile sensing. To do so, a robot needs to grasp within a pile, sense the number of objects in the grasp before lifting, and predict…
3D Human Pose Estimation in RGBD Images for Robotic Task Learning
We propose an approach to estimate 3D human pose in real world units from a single RGBD image and show that it exceeds performance of monocular 3D pose estimation approaches from color as well as pose estimation exclusiv…
3D Human Pose Estimation3D Pose EstimationPose Estimation