Capability-aware Task Allocation and Team Formation Analysis for Cooperative Exploration of Complex Environments

TL;DR

A multi-robot exploration mission is formulated and an operation policy to maintain robot team productivity and maximize mission success is computed to achieve autonomy in complex real-world exploration missions.

Abstract

To achieve autonomy in complex real-world exploration missions, we consider deployment strategies for a team of robots with heterogeneous autonomy capabilities. In this work, we formulate a multi-robot exploration mission and compute an operation policy to maintain robot team productivity and maximize mission rewards. The environment description, robot capability, and mission outcome are modeled as a Markov decision process (MDP). We also include constraints in real-world operation, such as sensor failures, limited communication coverage, and mobility-stressing elements. Then, we study the proposed operation model on a real-world scenario in the context of the DARPA Subterranean (SubT) Challenge. The computed deployment policy is also compared against the human-based operation strategy in the final competition of the SubT Challenge. Finally, using the proposed model, we discuss the design trade-off on building a multi-robot team with heterogeneous capabilities.

Figures (6)

• Figure 1: Robot team deployment underground in a Kentucky limestone mine. Robots with different mobility capabilities (i.e., wheeled, legged, aerial) are sent to the mine to collaboratively map the environment and find anomalies.
• Figure 2: Topological map representation with traversability factors.
• Figure 3: (a) The course map of the SubT Challenge Final Event which consists tunnel, urban, and cave environment. The location of the artifacts are annotated in yellow. (b) Team CoSTAR's robots on the staging area (located on the top left of the map). (c-e) Photos from different part of the course: tunnel (c), urban (d), and cave (e) environment. (f) Different type of terrain and environmental challenges in the course. The base map and photos are provided by DARPA. The annotations are added by the authors.
• Figure 4: Urban building exploration scenario inspired by DARPA SubT Challenge Urban Circuit. 7 sectors in two floors are connected with a staircase. Two robots (wheeled, legged) are deployed from the staging area.
• Figure 5: Visualization of robot team behaviors in nominal and contingency cases for the urban building scenario. In the nominal case, the optimal policy directs the legged robot to explore the lower level through stairs while the wheeled robot to explore the upper level. If the wheeled robot fails to move between sectors due to a traversability hazard, the legged robot on the lower level is guided to explore the remaining upper-floor sectors.