In robot navigation tasks, such as unmanned aerial vehicle (UAV) highway traffic monitoring, it is important for a mobile robot to follow a specified desired path. However, most of the existing path-following navigation algorithms cannot guarantee global convergence to desired paths or enable following self-intersected desired paths due to the existence of singular points where navigation algorithms return unreliable or even no solutions. One typical example arises in vector-field guided path-following (VF-PF) navigation algorithms . These algorithms are based on a vector field, and the singular points are exactly where the vector field diminishes. Conventional VF-PF algorithms generate a vector field of the same dimensions as those of the space where the desired path lives. In this article, we show that it is mathematically impossible for conventional VF-PF algorithms to achieve global convergence to desired paths that are self-intersected or even just simple closed (precisely, homeomorphic to the unit circle). Motivated by this new impossibility result, we propose a novel method to transform self-intersected or simple closed desired paths to nonself-intersected and unbounded (precisely, homeomorphic to the real line) counterparts in a higher dimensional space. Corresponding to this new desired path, we construct a singularity-free guiding vector field on a higher dimensional space. The integral curves of this new guiding vector field is thus exploited to enable global convergence to the higher dimensional desired path, and therefore the projection of the integral curves on a lower dimensional subspace converge to the physical (lower dimensional) desired path. Rigorous theoretical analysis is carried out for the theoretical results using dynamical systems theory. In addition, we show both by theoretical analysis and numerical simulations that our proposed method is an extension combining conventional VF-PF algorithms and trajectory tracking algorithms. Finally, to show the practical value of our proposed approach for complex engineering systems, we conduct outdoor experiments with a fixed-wing airplane in windy environment to follow both 2-D and 3-D desired paths.

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.

In the fight against COVID-19, many robots replace human employees in various tasks that involve a risk of infection. Among these tasks, the fundamental problem of navigating robots among crowds, named robot crowd navigation, remains open and challenging. Therefore, we propose HGAT-DRL, a heterogeneous GAT-based deep reinforcement learning algorithm. This algorithm encodes the constrained human-robot-coexisting environment in a heterogeneous graph consisting of four types of nodes. It also constructs an interactive agent-level representation for objects surrounding the robot, and incorporates the kinodynamic constraints from the non-holonomic motion model into the deep reinforcement learning (DRL) framework. Simulation results show that our proposed algorithm achieves a success rate of 92%, at least 6% higher than four baseline algorithms. Furthermore, the hardware experiment on a Fetch robot demonstrates our algorithm’s successful and convenient migration to real robots.

In this article, we propose a distributed guiding-vector-field (DGVF) algorithm for a team of robots to form a spontaneous-ordering platoon moving along a predefined desired path in the $n$ -dimensional Euclidean space. Particularly, by adding a path parameter as an additional virtual coordinate to each robot, the DGVF algorithm can eliminate the singular points where the vector fields vanish, and govern robots to approach a closed and even self-intersecting desired path. Then, the interactions among neighboring robots and a virtual target robot through their virtual coordinates enable the realization of the desired platoon; in particular, relative parametric displacements can be achieved with arbitrary ordering sequences. Rigorous analysis is provided to guarantee the global convergence of the spontaneous-ordering platoon on the common desired path from any initial positions. Two-dimensional experiments using three HUSTER-0.3 unmanned surface vessels (USVs) are conducted to validate the practical effectiveness of the proposed DGVF algorithm, and 3-D numerical simulations are presented to demonstrate its effectiveness and robustness when tackling higher dimensional multirobot path-navigation missions and some robots breakdown.

In this article, we propose coordinating guiding vector fields to achieve two tasks simultaneously with a team of robots: first, the guidance and navigation of multiple robots to possibly different paths or surfaces typically embedded in 2-D or 3-D, and second, their motion coordination while tracking their prescribed paths or surfaces. The motion coordination is defined by desired parametric displacements between robots on the path or surface. Such a desired displacement is achieved by controlling the virtual coordinates, which correspond to the path or surface's parameters, between guiding vector fields. Rigorous mathematical guarantees underpinned by dynamical systems theory and Lyapunov theory are provided for the effective distributed motion coordination and navigation of robots on paths or surfaces from all initial positions. As an example for practical robotic applications, we derive a control algorithm from the proposed coordinating guiding vector fields for a Dubins-car-like model with actuation saturation. Our proposed algorithm is distributed and scalable to an arbitrary number of robots. Furthermore, extensive illustrative simulations and fixed-wing aircraft outdoor experiments validate the effectiveness and robustness of our algorithm.

Accurately following a geometric desired path in a two-dimensional (2-D) space is a fundamental task for many engineering systems, in particular mobile robots. When the desired path is occluded by obstacles, it is necessary and crucial to temporarily deviate from the path for obstacle/collision avoidance. In this article, we develop a composite guiding vector field via the use of smooth bump functions and provide theoretical guarantees that the integral curves of the vector field can follow an arbitrary sufficiently smooth desired path and avoid collision with obstacles of arbitrary shapes. These two behaviors are reactive since path (re)planning and global map construction are not involved. To deal with the common deadlock problem, we introduce a switching vector field, and the Zeno behavior is excluded. Simulations are conducted to support the theoretical results.