A Shared-Autonomy Construction Robotic System for Overhead Works
🤖 AI Summary
Remote operation of construction robots in overhead tasks (e.g., ceiling drilling) suffers from limited visibility and frequent dynamic obstacles, compromising safety and reliability.
Method: This paper proposes a shared-autonomy construction robot system comprising a mobile base, a two-stage lifting mechanism, a dual-arm torso, a custom drilling end-effector, and RGB-D sensing. It integrates online Gaussian point-lattice 3D reconstruction with motion-aware dynamic object modeling, and employs a Neural Configuration-Space Barrier (Neural C-Space Barrier) for real-time, safety-guaranteed motion planning and adaptive control under dynamic occlusions.
Contribution/Results: Experiments demonstrate fully autonomous execution of end-to-end tasks—including drilling, bolt tightening, and anchoring—with significantly improved teleoperation safety and task success rates in dynamic environments. The framework provides a scalable, safety-critical autonomy architecture for embodied construction robots operating in complex, unstructured settings.
Application Category
📝 Abstract
We present the ongoing development of a robotic system for overhead work such as ceiling drilling. The hardware platform comprises a mobile base with a two-stage lift, on which a bimanual torso is mounted with a custom-designed drilling end effector and RGB-D cameras. To support teleoperation in dynamic environments with limited visibility, we use Gaussian splatting for online 3D reconstruction and introduce motion parameters to model moving objects. For safe operation around dynamic obstacles, we developed a neural configuration-space barrier approach for planning and control. Initial feasibility studies demonstrate the capability of the hardware in drilling, bolting, and anchoring, and the software in safe teleoperation in a dynamic environment.
Problem
Research questions and friction points this paper is trying to address.
Developing a robotic system for overhead construction tasks like ceiling drilling
Enabling safe teleoperation in dynamic environments with limited visibility
Creating motion planning for obstacle avoidance during construction operations
Innovation
Methods, ideas, or system contributions that make the work stand out.
Mobile robotic system with bimanual torso for overhead tasks
Gaussian splatting enables online 3D reconstruction in dynamic environments
Neural configuration-space barrier ensures safe obstacle avoidance
🔎 Similar Papers
No similar papers found.
