Motion planning in dynamic environments is a fundamental problem in robotics, aiming to generate safe and efficient paths, trajectories, or control actions in the presence of moving obstacles, uncertain predictions, and multi-agent interactions. It has broad applications in autonomous driving, service robotics, warehouse logistics, human-robot collaboration, crowd navigation, and multi-robot systems. This survey reviews representative works published primarily between 2015 and 2025, with a particular focus on how recent learning-based advances extend, complement, or interact with classical planning foundations. We first revisit classical planning methods as algorithmic foundations and reference frameworks for learning-based extensions. We then propose a role-of-learning taxonomy that categorizes existing methods according to how learning participates in the planning pipeline, including direct policy learning, learning-augmented classical planning, hybrid planning, and training enhancement methods. For each category, we summarize the main problem settings, representative algorithms, key ideas, integration mechanisms, strengths, and limitations. We further analyze how observation representations, prediction uncertainty, interaction modeling, planner integration, safety constraints, and training strategies shape learning-based motion planning in dynamic environments. Finally, we discuss open challenges and future directions, including sim-to-real gap, safe and certifiable planning, dense crowd navigation, perception-planning coupling, and embodied AI.
Zongyuan Shen, Shalabh Gupta, Shancheng Zhao et al.· 0 citations
Integrated sensing and communication (ISAC) under a cell-free (CF) architecture enables seamless connectivity and sensing coverage by allowing multiple distributed access points (APs) to jointly serve users and detect targets, thereby mitigating cell-edge effects and enhancing spatial diversity. However, wideband CF-ISAC also suffers from frequency-selective fading and strong inter-AP interference. To address these challenges, we investigate a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-assisted ISAC framework, which extends full-space coverage and mitigates multiplicative fading and blockage effects. A joint optimization strategy is developed to maximize the weighted ISAC joint rate by jointly optimizing bandwidth and power allocation, receive beamforming, and active STAR-RIS beamforming. To tackle the non-convexity caused by variable coupling and intricate constraints, an efficient alternating optimization algorithm is developed. The original problem is decomposed into several subproblems: first, a closed-form solution for receive beamforming is derived; next, the resource allocation semi-analytical solutions are obtained via Karush-Kuhn-Tucker (KKT) conditions. Subsequently, the active STAR-RIS coefficients are optimized by capitalizing on fractional programming and majorization-minimization (MM) techniques. Finally, simulation results reveal that the proposed scheme achieves a 20.34% weighted ISAC joint-rate gain over the passive scheme, validating its effectiveness in wideband CF-ISAC systems.
Xintong Zhou, Feng Ke, Xiuyin Zhang et al.· IEEE Transactions on Communi...· 0 citations