MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation

📅 2026-09-17
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
为解决长时序机器人操作中目标跟踪和任务进度评估的问题,提出MaskHarness-WAM系统,通过目标掩模连接高层规划与低层策略,利用视觉反馈实现连续执行。
📝 Abstract
Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout execution. This challenge becomes particularly critical when multiple objects share identical appearances and must be manipulated in a prescribed order. In such scenarios, relying solely on a limited-horizon manipulation policy is often insufficient to determine which instance should be operated on and when the task should transition to the next stage. To address this challenge, we propose MaskHarness-WAM, an instance-grounded harness for long-horizon manipulation. The proposed system connects high-level task planning with low-level manipulation policies through target masks, while leveraging visual feedback for subtask scheduling and continuous execution. Since each subtask corresponds to a different target instance, the low-level policy requires a newly established initial target mask under the updated scene at each subtask transition. The harness continuously re-observes the environment, generates, and verifies the target mask at subtask boundaries, thereby updating the instance-level spatial condition provided to the low-level policy. Furthermore, the system advances the manipulation process by switching target instances according to the verified completion status of each subtask. Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.
Problem

Research questions and friction points this paper is trying to address.

long-horizon manipulation
target tracking
task progress assessment
instance-grounded
Innovation

Methods, ideas, or system contributions that make the work stand out.

instance-grounded harness
target mask
subtask scheduling
visual feedback
long-horizon manipulation
💼 Related Jobs
No related jobs found.
Z
Zitai Huang
Tongji University; AIRC, Midea Group
T
Taiyi Su
AIRC, Midea Group
J
Jian Zhu
AIRC, Midea Group
Jianjun Zhang
Jianjun Zhang
South China University of Technology
machine learningneural networks
Chong Ma
Chong Ma
Southwest Jiaotong University
Deep LearningHuman Computer InteractionMedical Image Analysis
T
Tianbin Liu
AIRC, Midea Group
W
Weiyi Lu
AIRC, Midea Group
Y
Yi Xu
AIRC, Midea Group
Hanli Wang
Hanli Wang
Tongji University
Multimedia ComputingComputer VisionImage ProcessingMachine Learning