HEHA: Hierarchical Planning for Heterogeneous Multi-Robot Exploration of Unknown Environments

TL;DR

HEHA tackles autonomous exploration with heterogeneous robots by introducing a hierarchical planning framework that decouples global frontier routing from local kinodynamic planning. The global planner PEAF solves a min-max multi-Hamiltonian path problem under assignment constraints to rapidly yield bounded sub-optimal solutions, followed by post-optimization to balance workloads. The local planner accounts for heterogeneity via hetero-frontier costs and priority-based allocation to minimize redundant exploration. Across simulated maps and real-robot experiments, HEHA achieves substantial reductions in exploration time and reveals robust handling of terrain heterogeneity such as stairs, underlining its practical value for efficient multi-robot exploration.

Abstract

This paper considers the path planning problem for autonomous exploration of an unknown environment using multiple heterogeneous robots such as drones, wheeled, and legged robots, which have different capabilities to traverse complex terrains. A key challenge there is to intelligently allocate the robots to the unknown areas to be explored and determine the visiting order of those spaces subject to traversablity constraints, which leads to a large scale constrained optimization problem that needs to be quickly and iteratively solved every time when new space are explored. To address the challenge, we propose HEHA (Hierarchical Exploration with Heterogeneous Agents) by leveraging a recent hierarchical method that decompose the exploration into global planning and local planning. The major contribution in HEHA is its global planning, where we propose a new routing algorithm PEAF (Partial Anytime Focal search) that can quickly find bounded sub-optimal solutions to minimize the maximum path length among the agents subject to traversability constraints. Additionally, the local planner in HEHA also considers heterogeneity to avoid repeated and duplicated exploration among the robots. The experimental results show that, our HEHA can reduce up to 30% of the exploration time than the baselines.

Figures (5)

• Figure 1: Exploration using a ground vehicle (GV) and a legged vehicle (LV). (a) shows the results after exploration where the orange and red lines show the robots' trajectories. (b-d) are images of the real world for the areas (i-iii) in (a). The stairs in area (i) as shown in (b) is first found by GV but is only accessible by the LV. Our planner considers such traversability constraints during path planning. Our video attachment shows the exploration process.
• Figure 2: System Overview. (a) shows the global planning where the dashed window shows the local planning. The blue node in (a) is created since the GV explores the area as shown in (c). However, after the terrain analysis, the GV finds that the area can only be explored by an AV due to the obstacles, which thus sets the assignment constraint of the blue node in (a).
• Figure 3: (a) An example of global planning. The color of a target node indicates the assignment constraints. (b) The corresponding complete graph, where $v_s^i$, $v_g^i$ are the start and goal nodes of robots $i=1,2$ and $v_1,v_2,v_3$ are the target nodes to be visited. (c) A search label where robot $2$ can move to one available target node or goal node as the successors. (d) The MST heuristic of a label showed with the dashed lines, where the current nodes of robot $1,2$ are connected with zero-cost edge shown in blue.
• Figure 4: (a) shows an area (blue, node $v$) within the intersection between two robots' local planning regions. (b) shows that $v$ is assigned to the AV due to the high priority of AV. (c) shows that when constructing the TSP graph for local planning, the cost of the edge from the starting node to $v$ is modified to encourage early exploration of $v$. (d) shows the resulting plan.
• Figure 5: Exploration in three environments: Garden (A) A, Village (B), Forest (C). (i) shows the trajectories of the robots using Nearest, NBVP and Ours. (ii) shows the exploration rates over time.

Theorems & Definitions (1)

• Definition 1: Label Dominance