This work presents a prioritized Safe Interval Path Planning algorithm (SIPP-PP) with a novel limited goal reservation strategy to prevent goal-blocking conflicts while allowing shared goal regions, and demonstrates a multi-robot planner capable of real-time operation in dense scenarios, satisfying the stringent requirements of industrial applications such as drive units in fulfillment centers.
: This paper provides a thorough survey and integrative presentation of cooperative path planning for multi-robot systems operating in dynamic, cluttered, and partially observable environments. People synthesise algorithmic foundations ranging from heuristic graph search to sampling-based motion planners, including A*, D* Lite, and Safe Interval Path Planning for discrete/time-augmented spaces, as well as RRT, RRT*, and Informed RRT* for continuous configuration spaces. Multi-agent coordination techniques are reviewed, covering reciprocal collision avoidance (ORCA) and centralised Multi-Agent Path Finding (MAPF) solvers such as Conflict-Based Search (CBS) and bounded-suboptimal variants (ECBS). The paper also examine control and safety layers like Model Predictive Control and Control Barrier Functions that translate plans into dynamically feasible commands with safety guarantees. Recent progress in cooperative multi-agent reinforcement learning (MAPPO, QMIX, MADDPG) is evaluated for adaptability under partial observability and nonstationary environments. Applications in warehousing, intelligent transportation, and disaster response are used to illustrate practical trade-offs and integration patterns, referencing real-world systems such as Kiva-style warehouse fleets and autonomous driving pipelines. The paper concludes with a focused discussion on open challenges — scalability with guarantees, safety under uncertainty, sim-to-real transfer, and planning – control interface fragility — and proposes research directions including learning-augmented heuristics, unified safety-aware planning, adaptive MPC – CBF filters, and more informative benchmarks to drive reproducible progress.
Yun Pan· Proceedings of the 3rd Inter...· 0 citations
The autonomous execution of routine sequential tasks by mobile robots in obstacle-dense environments poses substantial challenges for long-duration operations, as it simultaneously demands energy efficiency, kinematically feasible trajectory generation, and collision-free maneuvering. Although genetic algorithms (GAs) have been successfully applied to such problems, they often struggle to converge toward a feasible solution space when initialized with random coordinates in complex multi-goal maps. To address these limitations, we propose a hierarchical path planning framework for multi-goal navigation. Population initialization is accelerated by integrating the deterministic seed path planning of A* with the multi-objective optimization capabilities of the Non-dominated Sorting GA II (NSGA-II). Subsequently, the following five conflicting criteria are simultaneously optimized over a B-Spline curve representation to ensure that the planned paths comply with the robot’s physical constraints: path length, cumulative wheel effort (energy consumption), trajectory curvature (smoothness), obstacle clearance (centering), and collision risk. We further introduce a softmin-based adaptive blending mechanism that automatically selects the most suitable path from the champion solutions on the Pareto front according to regional environmental conditions, thereby eliminating the need for manual user intervention. Extensive simulation results across five difficulty levels involving multiple segments demonstrate that the proposed adaptive NSGA-II method achieves path length improvements of 22%–42%, 8%–27%, and 16%–34% compared with Standard GA, ant-based whale optimization algorithm-artificial potential field, and HWPSO, respectively. The adaptive blending mechanism also attains the shortest mean path length in all five tested environments.
Osman Emre Turan, Oğuz Mısır, Mustafa Ozden· Measurement science and tech...· 0 citations
This work introduces a unified RL formulation that jointly optimizes agent and environment policies, where the environment policy learns graph edge costs to provide global movement guidance via backward Dijkstra search and achieves significant improvements over the strong search-based planner, Causal-PIBT, across multiple high-density maps.
He Jiang, Jingtian Yan, Yulun Zhang et al.· 0 citations
This study proposes a novel real-time trajectory planning framework designed to address the complex navigation challenges of collaborative robots operating in shared workspaces. The developed framework effectively integrates Model Predictive Path Integral (MPPI) control with Artificial Potential Field (APF) mechanisms to ensure robust and adaptive motion generation. To comprehensively evaluate its performance, the approach was validated in diverse environments, including no obstacle, high multi obstacle, and wall configurations, using complex setups of two, three, and four UR5 manipulators. Throughout these extensive tests, the proposed algorithm consistently achieved a 100% success rate in real-time collision avoidance while strictly adhering to the inherent kinematic limits of the robots. Comparative analyses further highlighted the superior efficiency of this method. In the most challenging environment, the proposed framework outperformed a baseline jerk-and-acceleration controller by completing operations 21.3% faster with a 3.8% lower jerk, and significantly surpassed a pure acceleration controller with a 41% faster operation time alongside a 16.7% reduction in jerk.
Nezih Bora Yavas, Zafer Bingul· 2026 IEEE/ASME International...· 0 citations
To address the challenge of achieving efficient and safe autonomous navigation for mobile robots in complex dynamic environments, this paper proposes a hierarchical planning architecture based on point-by-point tracking control. A node detection strategy grounded in the safe workspace effectively prevents collisions between the generated path and surrounding obstacles. A two-stage heuristic search strategy is designed, incorporating an intermediate node mechanism to substantially enhance search efficiency. Furthermore, the potential field model of the Artificial Potential Field (APF) method is optimized, and a node attraction strategy is introduced to improve overall path quality. Simulation results demonstrate that, compared to baseline algorithms, the global planner achieves significant improvements in path length, computation time, and the number of sampling iterations. The local planner also exhibits superior performance in both computation time and path quality relative to other comparative algorithms. Finally, both ROS-based simulations and physical experiments validate that the proposed hierarchical planning framework delivers exceptional path planning efficiency and obstacle avoidance capability in complex dynamic environments.
Xinguang Li, Shilong Zhao, Xiaoqin Guo· Proceedings of the Instituti...· 0 citations
Over the past decade, autonomous robotic systems have been increasingly deployed in applications such as surveying, search and rescue, and last-mile delivery. These applications require robots to generate safe and efficient motion plans in large, complex, and obstacle-dense environments, often under limited onboard computing resources. However, conventional planning methods commonly rely on finite-dimensional trajectory parameterization or increasingly long prediction horizons, leading to rapidly growing computational costs, particularly in multi-robot scenarios. This paper presents a novel variation-based iterative-learning planning (VIP) framework for efficient motion planning of both single robots and robotic swarms. Instead of optimizing a large number of discrete trajectory variables, VIP directly updates the planning command as a continuous function in an infinite-dimensional function space. The same variation-based update can be implemented in a model-in-the-loop manner for offline planning or in a robot-in-the-loop manner between online physical executions. By avoiding the computational burden associated with horizon expansion and high-dimensional trajectory discretization, VIP maintains a per-iteration computational complexity of $\mathcal{O}(n)$, where $n$ denotes the number of spatial discretization points. Extensive simulations and real-world experiments demonstrate that the proposed framework can efficiently generate and iteratively improve motion plans for different planning objectives, robotic platforms, and swarm configurations, highlighting its effectiveness, computational efficiency, and scalability as a general planning methodology.
Shuli Lv, Pengda Mao, Chen Min et al.· 0 citations