Traditional sampling-based algorithms rely on random samples to explore a whole configuration space of robots for optimal path planning, while a uniform sampler impedes the exploration with randomly generated samples, leading to a long calculation time, especially in complex environments. Recently, neural-network-driven methods have attracted wide interest in developing non-uniform sampling to improve the sampling efficiency and reduce the calculation time. A region that contains an optimal path is predicted by neural networks and employed subsequently to biasedly generate samples. This work aims at enhancing the sampling efficiency and reducing the calculation time of the optimal path planning by a novel region and guideline prediction (denoted as RGP) model. We innovatively propose the RGP model with a guideline prediction module to estimate the guideline distributions, which are characterized by the central line of the predicted region. The predicted region and guideline are integrated into a sampling-based algorithm, namely RGP-RRT*, with an adaptively biased sampling strategy to select a proper domain for sampling. Simulations demonstrate the RGP model outperforms other region prediction models in accuracy and robustness. Besides, the RGP-RRT* reliably achieves a 7.2–80.1% reduction in calculation time and a 2.0–58.1% reduction in sample number compared with other neural-network-driven methods.

As technology rapidly evolves, the application of bipedal robots in various environments has widely expanded. These robots, compared to their wheeled counterparts, exhibit a greater degree of freedom and a higher complexity in control, making the challenge of maintaining balance and stability under changing wind speeds particularly intricate. Overcoming this challenge is critical as it enables bipedal robots to sustain more stable gaits during outdoor tasks, thereby increasing safety and enhancing operational efficiency in outdoor settings. To transcend the constraints of existing methodologies, this research introduces an adaptive bio-inspired exploration framework for bipedal robots facing wind disturbances, which is based on the Deep Deterministic Policy Gradient (DDPG) approach. This framework allows the robots to perceive their bodily states through wind force inputs and adaptively modify their exploration coefficients. Additionally, to address the convergence challenges posed by sparse rewards, this study incorporates Hindsight Experience Replay (HER) and a reward-reshaping strategy to provide safer and more effective training guidance for the agents. Simulation outcomes reveal that robots utilizing this advanced method can more swiftly explore behaviors that contribute to stability in complex conditions, and demonstrate improvements in training speed and walking distance over traditional DDPG algorithms.

Multi-goal path finding (MGPF) aims to find a closed and collision-free path to visit a sequence of goals orderly. As a physical travelling salesman problem, an undirected complete graph with accurate weights is crucial for determining the visiting order. Lack of prior knowledge of local paths between vertices poses challenges in meeting the optimality and efficiency requirements of algorithms. In this study, a multi-task learning model designated Prior Knowledge Extraction (PKE), is designed to estimate the local path length between pairwise vertices as the weights of the graph. Simultaneously, a promising region and a guideline are predicted as heuristics for the path-finding process. Utilizing the outputs of the PKE model, a variant of Rapidly-exploring Random Tree (RRT) is proposed known as PKE-RRT. It effectively tackles the MGPF problem by a local planner incorporating a prioritized visiting order, which is obtained from the complete graph. Furthermore, the predicted region and guideline facilitate efficient exploration of the tree structure, enabling the algorithm to rapidly provide a sub-optimal solution. Extensive numerical experiments demonstrate the outstanding performance of the PKE-RRT for the MGPF problem with a different number of goals, in terms of calculation time, path cost, sample number, and success rate.