Cooperative Multi-Robot Task Allocation with Reinforcement Learning

This paper deals with the concept of multi-robot task allocation, referring to the assignment of multiple robots to tasks such that an objective function is maximized. The performance of existing meta-heuristic methods worsens as the number of robots or tasks increases. To tackle this problem, a novel Markov decision process formulation for multi-robot task allocation is presented for reinforcement learning. The proposed formulation sequentially allocates robots to tasks to minimize the total time taken to complete them. Additionally, we propose a deep reinforcement learning method to find the best allocation schedule for each problem. Our method adopts the cross-attention mechanism to compute the preference of robots to tasks. The experimental results show that the proposed method finds better solutions than meta-heuristic methods, especially when solving large-scale allocation problems.

Distributed multi-robot sweep coverage for a region with unknown workload distribution

This paper considers the scenario where multiple robots collaboratively cover a region in which the exact distribution of workload is unknown prior to the operation. The workload distribution is not uniform in the region, meaning that the time required to cover a unit area varies at different locations of the region. In our approach, we divide the target region into multiple horizontal stripes, and the robots sweep the current stripe while partitioning the next stripe concurrently. We propose a distributed workload partition algorithm and prove that the operation time on each stripe converges to the minimum under the discrete-time update law. We conduct comprehensive simulation studies and compare our method with the existing methods to verify the theoretical results and the advantage of the proposed method. Flight experiments on mini drones are also conducted to demonstrate the practicality of the proposed algorithm.

Multirobot Formation with Sensor Fusion-Based Localization in Unknown Environment

Multirobot cooperation enhancing the efficiency of numerous applications such as maintenance, rescue, inspection in cluttered unknown environments is the interesting topic recently. However, designing a formation strategy for multiple robots which enables the agents to follow the predefined master robot during navigation actions without a prebuilt map is challenging due to the uncertainties of self-localization and motion control. In this paper, we present a multirobot system to form the symmetrical patterns effectively within the unknown environment deployed randomly. To enable self-localization during group formatting, we propose the sensor fusion system leveraging sensor fusion from the ultrawideband-based positioning system, Inertial Measurement Unit orientation system, and wheel encoder to estimate robot locations precisely. Moreover, we propose a global path planning algorithm considering the kinematic of the robot’s action inside the workspace as a metric space. Experiments are conducted on a set of robots called Falcon with a conventional four-wheel skid steering schematic as a case study to validate our proposed path planning technique. The outcome of our trials shows that the proposed approach produces exact robot locations after sensor fusion with the feasible formation tracking of multiple robots system on the simulated and real-world experiments.