This paper proposes a nested kino-dynamic framework for rapid feasibility checking and dynamically consistent trajectory generation given a candidate contact sequence and shows that the generated trajectories can be tracked using a reinforcement learning (RL)-based controller and are of sufficiently high quality for execution in real-world loco-manipulation scenarios.
Abstract
Fast planning of novel behaviors in unseen scenarios remains a fundamental challenge in robotics. The high-dimensional, hybrid, and underactuated nature of humanoid loco-manipulation continues to hinder the realization of this goal. In this paper, we address this challenge by proposing a nested kino-dynamic framework for rapid feasibility checking and dynamically consistent trajectory generation given a candidate contact sequence. By integrating this module with a feasibility-guided tree search and a Large Language Model (LLM)-based contact plan sampling strategy, we demonstrate that the proposed framework can substantially improve the search process. Furthermore, we show that the generated trajectories can be tracked using a reinforcement learning (RL)-based controller and show that the resulting trajectories are of sufficiently high quality for execution in real-world loco-manipulation scenarios. A supplementary video is available at: https://youtu.be/R6qCHoCormQ.
This follow-up work tests the feasibility of the neuro-inspired self-supervised learning framework for trajectory planning that leverages forward and inverse models as the internal supervisory mechanism in an environment that contains an obstacle, and demonstrates the tendency of the planner to exploit the learning signal provided by the forward and inverse models.
Miroslav Krupa, Miroslav Cibula, Kristína Malinovská· 0 citations
This work introduces Model-Based Diffusion Optimal Control (MDOC), a model-based diffusion planner that efficiently produces dynamically feasible trajectories without relying on data, and shows that MDOC's safety mechanism naturally scales to multi-robot planning settings through Conflict-Based Search.
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
Hyper-redundant robots are essential for navigation in highly constrained environments, yet their high-dimensional kinematics impose a severe computational burden on real-time motion planning. While optimization-based methods ensure tracking precision, their high computational latency makes them unsuitable for online feedback loops; conversely, geometric heuristics offer speed but lack kinematic fidelity. To resolve this efficiency-accuracy trade-off, we present an imitation learning framework tailored for path-following tasks. First, to address the instability of expert data generation caused by non-differentiable minimax objectives, we propose a refined Soft-Maximum formulation that produces smooth, kinetically consistent demonstrations. Second, we mitigate the covariate shift inherent in Behavior Cloning (BC) through a two-stage noise-injection curriculum, enabling the agent to learn robust recovery policies entirely offline without requiring an interactive expert. Finally, we design a structured policy network that effectively fuses high-dimensional path descriptors with low-dimensional proprioceptive states. Extensive simulations demonstrate that our approach achieves optimization-level accuracy with inference speeds comparable to geometric heuristics, validating its efficacy for high-precision inspection tasks.
Nailong Bu, Ningyuan Luo, Chao-yuan Liu et al.· 2026 IEEE/ASME International...· 0 citations
This work uses Sample-based Model Predictive Control entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets and validate the robustness of this sim-to-real framework by successfully deploying complex loco-manipulation skills across different morphologies.
Martin Schuck, Maks Sorokin, S. Manni et al.· 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