SLEI3D: Simultaneous Exploration and Inspection via Heterogeneous Fleets under Limited Communication

TL;DR

This work tackles the challenge of simultaneous exploration, inspection, and communication in large-scale, unknown 3D environments using heterogeneous robotic fleets under limited communication. It introduces SLEI3D, a two-layer, multi-rate coordination framework that orchestrates GCS-to-SubGroups and intra-subgroup collaboration, guided by bounding-box priors to constrain exploration, and employs FF3E for frontier-based exploration and SOEI for proactive inspection scheduling. The approach is formalized as a joint optimization with mechanisms for time-prediction, meeting-time planning, and adaptive online execution, and is validated through extensive simulations (up to 48 robots and 384k m$^3$) and hardware experiments with 7 robots, including scenarios with robot failures and energy constraints. Results show improved mission efficiency, reduced idle time, and robust performance across fully unknown, heterogeneous, and energy-limited settings, highlighting practical impact for large-scale inspection campaigns in challenging environments.

Abstract

Robotic fleets such as unmanned aerial and ground vehicles have been widely used for routine inspections of static environments, where the areas of interest are known and planned in advance. However, in many applications, such areas of interest are unknown and should be identified online during exploration. Thus, this paper considers the problem of simultaneous exploration, inspection of unknown environments and then real-time communication to a mobile ground control station to report the findings. The heterogeneous robots are equipped with different sensors, e.g., long-range lidars for fast exploration and close-range cameras for detailed inspection. Furthermore, global communication is often unavailable in such environments, where the robots can only communicate with each other via ad-hoc wireless networks when they are in close proximity and free of obstruction. This work proposes a novel planning and coordination framework (SLEI3D) that integrates the online strategies for collaborative 3D exploration, adaptive inspection and timely communication (via the intermit-tent or proactive protocols). To account for uncertainties w.r.t. the number and location of features, a multi-layer and multi-rate planning mechanism is developed for inter-and-intra robot subgroups, to actively meet and coordinate their local plans. The proposed framework is validated extensively via high-fidelity simulations of numerous large-scale missions with up to 48 robots and 384 thousand cubic meters. Hardware experiments of 7 robots are also conducted. Project website is available at https://junfengchen-robotics.github.io/SLEI3D/.

Figures (29)

• Figure 1: (a)$6$ explorers and $12$ inspectors are tasked to simultaneously explore and inspect an unknown number of numerous features; (b) the explorer and inspectors within the same subgroup coordinate for the inspection tasks; (c) the mobile ground station actively meets with the explorers to receive the latest features; (d)-(g) snapshots of online execution in four different large-scale scenes.
• Figure 2: Overview of the proposed method, which consists of two hierarchical layers: the first layer where GCS coordinates with explorers, and the second layer where the explorer coordinates with inspectors within each subgroup, all under limited communication.
• Figure 3: Intermittent communication between GCS and explorers.
• Figure 4: BBoxes Construction via the vertical buildings (left) for two scenarios; Adaptive BBox partition without any priors (right).
• Figure 5: Fast frontier-based exploration and local adaptation of the exploration strategy $\{\mathbf{p}^t_i\}$ by the explorer.

Theorems & Definitions (10)

• Example 1
• Remark 1
• Remark 2
• Lemma 1
• proof
• Definition 1: Plan of Subgroup
• Lemma 2
• proof
• Theorem 1
• proof