paper-with-me

홈 › Papers

Sequential Planning via Anchored Robotic Keypoints

2026-06-29 · Bryce Grant, Aryeh Rothenberg, Logan Senning, Zonghe Chua, Zach Patterson, Peng Wang arxiv

We present Sequential Planning via Anchored Robotic Keypoints, SPARK, a training-free neurosymbolic manipulation system that reaches 43.7% on six LIBERO-PRO position \& task cells, more than doubling CaP-Agent0 and Vision-Language-Action (VLA) baselines. CaP-Agent0, a multi-turn code-generation agent, achieves 18.2% by re-querying an LLM at every turn, but its restart-from-scratch solution proves costly against minor policy failures. Perception is the layer that fails most under position and task changes so SPARK spends its computation there. A single Gemini call composes the plan as a typed behavior tree (BT) of composable primitives, each already containing the low-level control (motion, grasping, depth geometry) a code-generation agent would otherwise regenerate on every trial. The rest of the budget goes to perception: a second Gemini call proposes three alternative text prompts per object, SAM3 evaluates each, and we keep the prompt$\to$label pair with the most confident detection and a recovery loop then retries a failed primitive against freshly detected objects, with no new LLM call. The alternative prompts add +27.7 points on the spatial suite and +10.0 on the object suite, with the recovery loop adding +5.0 overall. SPARK runs the same primitives on three robot families (UR10e, Franka FR3, bimanual Franka) across nine unique tasks at twenty trials each, averaging 68%. Since the detector, planner, and controller modules sit behind the typed plan, they swap independently without training, and each primitive's checkable post-condition traces a failure to the corresponding module or a kinematic limit. Every trial logs a verified, labeled trajectory, so a training-free planner that already beats VLAs can supply the data those policies need without teleoperation. Project page: https://cwru-aism.github.io/spark-page/

📄 PDF Abstract BibTeX arXiv:2606.30613

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

3D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTS

2026-04-13 · Bronislav Sidik, Dror Mizrahi arxiv

We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS) with a 3D-consistent world model as the rollout oracle. Unlike reactiv…

KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation

2025-03-13 · Zixian Liu, Mingtong Zhang, Yunzhu Li

With the rapid advancement of large language models (LLMs) and vision-language models (VLMs), significant progress has been made in developing open-vocabulary robotic manipulation systems. However, many existing approach…

ObjectVisual Prompting

End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation

2022-02-12 · Tianying Wang, En Yen Puang, Marcus Lee, Yan Wu 외

We present an end-to-end Reinforcement Learning(RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state re…

reinforcement-learningReinforcement Learning (RL)

Pose Estimation for Robot Manipulators via Keypoint Optimization and Sim-to-Real Transfer

2020-10-15 · Jingpei Lu, Florian Richter, Michael Yip

Keypoint detection is an essential building block for many robotic applications like motion capture and pose estimation. Historically, keypoints are detected using uniquely engineered markers such as checkerboards or fid…

Keypoint DetectionPose Estimation

SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes

2024-08-05 · Mohammad Zohaib, Luca Cosmo, Alessio Del Bue

Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming. As keypoints should be semantically and geometrically consistent across all the…