Coverage First Next Best View for Inspection of Cluttered Pipe Networks Using Mobile Manipulators

Joshua Raymond Bettles; Jiaxu Wu; Bruno Vilhena Adorno; Joaquin Carrasco; Atsushi Yamashita

cs.ROMar 17, 2026

Coverage First Next Best View for Inspection of Cluttered Pipe Networks Using Mobile Manipulators

Authors: Joshua Raymond Bettles, Jiaxu Wu, Bruno Vilhena Adorno, Joaquin Carrasco, Atsushi Yamashita

Organizations: Manchester Centre for Robotics and AI, The University of Manchester, Manchester, UK. · The University of Tokyo, Tokyo, Japan.

Abstract

Robotic inspection of radioactive areas enables operators to be removed from hazardous environments; however, planning and operating in confined, cluttered environments remain challenging. These systems must autonomously reconstruct the unknown environment and cover its surfaces, whilst estimating and avoiding collisions with objects in the environment. In this paper, we propose a new planning approach based on next-best-view that enables simultaneous exploration and exploitation of the environment by reformulating the coverage path planning problem in terms of information gain. To handle obstacle avoidance under uncertainty, we extend the vector-field-inequalities framework to explicitly account for stochastic measurements of geometric primitives in the environment via chance constraints in a constrained optimal control law. The stochastic constraints were evaluated experimentally alongside the planner on a mobile manipulator in a confined environment to inspect a pipe network. These experiments demonstrate that the system can autonomously plan and execute inspection and coverage paths to reconstruct and fully cover the simplified pipe network. Moreover, the system successfully estimated geometric primitives online and avoided collisions during motion between viewpoints.

Figures & tables

	Parameter	Value
Sensor Configuration	RGB-D field of view (FoV)	$(60^{\circ},45^{\circ})$
	RGB-D maximum range	$3\,\mathrm{m}$
	Radiation sensor radius	$0.4\,\mathrm{m}$
Controller Parameters	$(\alpha,\kappa,\lambda_{c})$	$(0.7,6,1.2)$
	$(\lambda_{s},\eta)$	$(5\cdot 10^{3},1)$
	Point-to-plane $d_{\mathrm{safe}}$ (arm, base)	$(0.1,0.5)\,\mathrm{m}$

TABLE I : Experimental Parameters

Fig. 1 : The experimental setup with the constructed mobile manipulator in a single-pipe environment, overlaid with the radiation sensor model represented as a sphere in red, centred on $\mathcal{F}_{\mathrm{sensor}}$ , and the depth sensor model represented by the cameras’ FoV in pink.

Panel of Figure 3 — Fig. 2 : Time response of the closed-loop system from one trial in the three-pipe environment: (a) control input for the base, (b) control input for the arm, (c) norm of the task-space error, (d) distance to planes, and (e) distance to pipe constraints for the mobile manipulator in the confined space. Horizontal red dashed lines represent limits for the associated variables, whereas vertical black dashed lines represent the selection of a new set point.

Panel of Figure 4 — Fig. 3 : Results of the CFNBV planner within the three-pipe environment with the mean value of the five trials displayed with the maximum and minimum values overlaid. (a) The evolution of the voxels and their categorisation based on the visual and coverage sensors, (b) the minimisation of the combined entropy per voxel, and (c) the interplay between the IGs for environment exploration and surface exploitation.

Chance-Constrained Motion Planning

See all 11 papers

OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
Mar 10, 2026Boxun Hu, Chang Chang, Jiawei Ge +4Active Perception Next-Best-View Planning
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA +1
OmniPlanner: Universal Exploration and Inspection Path Planning Across Robot Morphologies
Mar 4, 2026Angelos Zacharia, Mihir Dharmadhikari, Mohit Singh +1Robotic Inspection Robot Task Planning
Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), 7034 Trondheim, Norway
Coverage Path Planning: Classical Foundations, Recent Advances, and Future Directions
Jul 12, 2026Zongyuan Shen, Shalabh Gupta, Shancheng Zhao +6Motion Planning Coverage Path Planning
College of Information Science and Technology, Jinan University, Guangzhou 510632, China. · Department of Electrical and Computer Engineering, University of Connecticut, Storrs, CT 06269, USA. · Global College, Shanghai Jiao Tong University, Shanghai 200240, China. +3

Mar 10, 2026J/K move · Enter open · S save

OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots

Boxun Hu, Chang Chang, Jiawei Ge, Man Namgung+3

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA+1

Active Perception Next-Best-View Planning Mobile Robotics Active View Selection Robot Motion Planning

Open paper AskPDF arXiv

We naturally step sideways or lean to see around the obstacle when our view is blocked, and recover a more informative observation. Enabling robots to make the same kind of viewpoint choice is critical for human-centered operations, including search, triage, and disaster response, where cluttered environments and partial visibility frequently degrade downstream perception. However, many Next-Best-View (NBV) methods primarily optimize generic exploration or long-horizon coverage, and do not explicitly target the immediate goal of obtaining a single usable observation of a partially occluded person under real motion constraints. We present Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots (OA-NBV), an occlusion-aware NBV pipeline that autonomously selects the next traversable viewpoint to obtain a more complete view of an occluded human. OA-NBV integrates perception and motion planning by scoring candidate viewpoints using a target-centric visibility model that accounts for occlusion, target scale, and target completeness, while restricting candidates to feasible robot poses. OA-NBV achieves over 90% success rate in both simulation and real-world trials, while baseline NBV methods degrade sharply under occlusion. Beyond success rate, OA-NBV improves observation quality: compared to the strongest baseline, it increases normalized target area by at least 81% and keypoint visibility by at least 58% across settings, making it a drop-in view-selection module for diverse human-centered downstream tasks.

Abstract

Chance-Constrained Motion Planning

Explore similar work

OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots

OmniPlanner: Universal Exploration and Inspection Path Planning Across Robot Morphologies

Coverage Path Planning: Classical Foundations, Recent Advances, and Future Directions