17 August 2020 in IEEE Access
In this paper, we apply deep reinforcement learning (DRL) to solve the flocking control problem of multi-robot systems in complex environments with dynamic obstacles. Starting from the traditional flocking model, we propose a DRL framework for implementing multi-robot flocking control, eliminating the tedious work of modeling and control designing. We adopt the multi-agent deep deterministic policy gradient (MADDPG) algorithm, which additionally uses the information of multiple robots in the learning process to better predict the actions that robots will take. To address the problems such as low learning efficiency and slow convergence speed of the MADDPG algorithm, this paper studies a prioritized experience replay (PER) mechanism and proposes the Prioritized Experience Replay-MADDPG (PER-MADDPG) algorithm. Based on the temporal difference (TD) error, a priority evaluation function is designed to determine which experiences are sampled preferentially from the replay buffer. In the end, the simulation results verify the effectiveness of the proposed algorithm. It has a faster convergence speed and enables the robot group to complete the flocking task in the environment with obstacles.
17 March 2022 in Applied Intelligence
14 April 2025 in IEEE Robotics and Automation Letters
In recent years, there has been a significant amount of research on algorithms and control methods for distributed collaborative robots. However, the emergence of collective behavior in a swarm is still difficult to predict and control. Nevertheless, human interaction with the swarm helps render the swarm more predictable and controllable, as human operators can utilize intuition or knowledge that is not always available to the swarm. Therefore, this letter designs the Dynamic Visualization Research Platform for Multimodal Human-Swarm Interaction (DVRP-MHSI), which is an innovative open system that can perform real-time dynamic visualization and is specifically designed to accommodate a multitude of interaction modalities (such as brain-computer, eye-tracking, electromyographic, and touch-based interfaces), thereby expediting progress in human-swarm interaction research. Specifically, the platform consists of custom-made low-cost omnidirectional wheeled mobile robots, multitouch screens and two workstations. In particular, the mutitouch screens can recognize human gestures and the shapes of objects placed on them, and they can also dynamically render diverse scenes. One of the workstations processes communication information within robots and the other one implements human-robot interaction methods. The development of DVRP-MHSI frees researchers from hardware or software details and allows them to focus on versatile swarm algorithms and human-swarm interaction methods without being limited to predefined and static scenarios, tasks, and interfaces. The effectiveness and potential of the platform for human-swarm interaction studies are validated by several demonstrative experiments.
17 February 2025 in arXiv
Human-multi-robot shared control leverages human decision-making and robotic autonomy to enhance human-robot collaboration. While widely studied, existing systems often adopt a leader-follower model, limiting robot autonomy to some extent. Besides, a human is required to directly participate in the motion control of robots through teleoperation, which significantly burdens the operator. To alleviate these two issues, we propose a layered shared control computing framework using human-influenced guiding vector fields (HI-GVF) for human-robot collaboration. HI-GVF guides the multi-robot system along a desired path specified by the human. Then, an intention field is designed to merge the human and robot intentions, accelerating the propagation of the human intention within the multi-robot system. Moreover, we give the stability analysis of the proposed model and use collision avoidance based on safety barrier certificates to fine-tune the velocity. Eventually, considering the firefighting task as an example scenario, we conduct simulations and experiments using multiple human-robot interfaces (brain-computer interface, myoelectric wristband, eye-tracking), and the results demonstrate that our proposed approach boosts the effectiveness and performance of the task.