Search Results (79)

This paper presents a kinematics-constrained grid-based path planning algorithm that generates real-time, safe, and executable trajectories, thereby enhancing the performance and reliability of autonomous vehicle parking systems. The grid resolution adapts to the minimum turning radius and steering limits, ensuring feasible motion primitives. The cost function integrates path efficiency, direction-switching penalties, and collision risk to ensure smooth and feasible maneuvers. A cubic spline refinement produces curvature-continuous trajectories suitable for vehicle execution. Simulation and experimental results demonstrate that the proposed method achieves collision-free and curvature-bounded paths with significantly reduced computation time and improved maneuver smoothness compared with conventional A* and Hybrid A*. In both structured and dynamic parking environments, the planner consistently maintained safe clearance and stable tracking performance under variations in vehicle geometry and velocity. These results confirm the robustness and real-time feasibility of the proposed approach, effectively unifying kinematic feasibility, safety, and computational efficiency for practical autonomous parking systems. Full article

Purcell’s three-link swimmers, characterised by segments connected through one-degree-of-freedom joints, exhibit a difficulty in following precise paths. This is attributed to their motion primitives, which do not inherently generate displacement in a singular, predictable direction. To overcome this limitation, this paper proposes a closed-loop control strategy on the basis of event-based control. This control approach enables the robot to perform a specific motion primitive when the deviation from the desired trajectory exceeds a predefined threshold. In other words, an asynchronous strategy is used to adjust the motion of the swimmer, thereby ensuring tracking of the desired path with a limited error. The effectiveness of this closed-loop control strategy is demonstrated through experiments with a motor-driven 30 cm-length prototype. These tests show that this event-based control strategy allows the swimmer to follow specific paths with a tracking error of less than 30% of its length. Full article

Oyster aquaculture in the U.S. faces severe inefficiencies due to the absence of precise path planning tools, resulting in environmental degradation and resource waste. Current dredging techniques lack trajectory planning, often leading to redundant seabed disturbance and suboptimal shell distribution. Existing vessel models—such as the Nomoto or Dubins models—are not designed to map steering inputs directly to spatial coordinates, presenting a research gap in maneuver planning for underactuated boats. This research fills that gap by introducing a novel hybrid vessel kinetics model that integrates the Nomoto model with Dubins motion primitives. Our approach links steering inputs directly to the vessel motion, enabling Cartesian coordinate path generation without relying on intermediate variables like yaw velocity. Field trials in the Chesapeake Bay demonstrate consistent trajectory following performance across varied path complexities, with average offsets of 0.01 m, 1.35 m, and 0.42 m. This work represents a scalable, efficient step toward real-time, constraint-aware automation in oyster harvesting, with broader implications for sustainable aquaculture operations. Full article

Traditional Chinese Bone-setting (TCB) involves complex movements and force feedback, which are critical for effective fracture reduction. However, its practice necessitates the collaboration of highly experienced surgeons, and the availability of expert resources is significantly limited. These challenges have significantly hindered the inheritance and dissemination of TCB techniques. The advancement of Learning from Demonstration offers a promising solution for addressing this challenge. In this study, we developed an innovative framework of closed reduction skill learning and dual-layer hybrid admittance control for a dual-arm bone-setting robot, specifically targeting ankle fracture. The framework began with a comprehensive structural design of the robot, incorporating analyses of closed-chain kinematics and the decomposition of internal and external forces. Additionally, we introduced a globally optimal reparameterization algorithm for temporal alignment of demonstrations and extended the Motion/Force Synchronous Kernelized Movement Primitive to learn reduction maneuvers and forces. Furthermore, we designed a dual-layer hybrid admittance controller, consisting of an ankle-layer and a robot- layer. Specifically, we propose a novel adaptive fuzzy variable admittance control strategy for the ankle-layer to achieve accurate tracking of reduction forces, which reduces the RMSE of force tracking along the X-axis by 50.35% compared to the non-fuzzy strategy. The experimental results demonstrated that the framework successfully replicates the human-like bone-setting process and can imitate personalized bone-setting trajectories under expert guidance. Full article

Feature point detection in inverse synthetic aperture radar (ISAR) images of space targets is the foundation for tasks such as analyzing space target motion intent and predicting on-orbit status. Traditional feature point detection methods perform poorly when confronted with the low texture and uneven brightness characteristics of ISAR images. Due to the nonlinear mapping capabilities, neural networks can effectively learn features from ISAR images of space targets, providing new ideas for feature point detection. However, the scarcity of labeled ISAR image data for space targets presents a challenge for research. To address the issue, this paper introduces a self-supervised feature point detection method (SFPD), which can accurately detect the positions of feature points in ISAR images of space targets without true feature point positions during the training process. Firstly, this paper simulates an ISAR primitive dataset and uses it to train the proposed basic feature point detection model. Subsequently, the basic feature point detection model and affine transformation are utilized to label pseudo-ground truth for ISAR images of space targets. Eventually, the labeled ISAR image dataset is used to train SFPD. Therefore, SFPD can be trained without requiring ground truth for the ISAR image dataset. The experiments demonstrate that SFPD has better performance in feature point detection and feature point matching than usual algorithms. Full article

Motion primitives are a highly useful and widely employed tool in the field of Learning from Demonstration (LfD). However, obtaining a large number of motion primitives can be a tedious process, as they typically need to be generated individually for each task to be learned. To address this challenge, this work presents an algorithm for acquiring robotic skills through automatic and unsupervised segmentation. The algorithm divides tasks into simpler subtasks and generates motion primitive libraries that group common subtasks for use in subsequent learning processes. Our algorithm is based on an initial segmentation step using a heuristic method, followed by probabilistic clustering with Gaussian Mixture Models. Once the segments are obtained, they are grouped using Gaussian Optimal Transport on the Gaussian Processes (GPs) of each segment group, comparing their similarities through the energy cost of transforming one GP into another. This process requires no prior knowledge, it is entirely autonomous, and supports multimodal information. The algorithm enables generating trajectories suitable for robotic tasks, establishing simple primitives that encapsulate the structure of the movements to be performed. Its effectiveness has been validated in manipulation tasks with a real robot, as well as through comparisons with state-of-the-art algorithms. Full article

In-hand manipulation with Cartesian-force-control-based pushing primitives is introduced to achieve the precise placement of an object in a desired position at a manufacturing site. In the bin picking process, achieving the desired grasping posture is challenging due to limitations in the sensing and control of the robotic arm, interference from clustered objects, and unintended collisions, which hinder achieving the planned pose. Even under such conditions, in cases that require precise operations, such as manufacturing processes, maintaining a desired placement posture is crucial for the precise placement of objects into the machine slot. In this paper, a pushing primitive incorporating force feedback control is applied to ensure that the gripper is consistently positioned at the edge of the grasped object regardless of the initial grasping position by utilizing the surrounding environment of the processing machine. Modeling the exact contact friction between the gripper and the grasped object is challenging; therefore, instead of relying on a motion planning approach, we addressed the problem using a control method that leverages feedback from the external force information of the robot manipulator. Additional sensors such as external cameras or tactile sensors in the gripper are not required. The pushing primitive is executed by applying a force greater than the frictional force between the gripper and the grasped object, leveraging the surrounding environment. Experimental verification confirmed that the proposed method achieves precise placement into the machine slot, regardless of initial grasping positions. It also proved to be effective on an actual testbed. Full article

Legged climbing unmanned ground vehicles (LC-UGVs) possess obstacle avoidance and wall transition capabilities, allowing them to move in 3D environments. Existing navigation methods for legged UGVs are only suitable for ground locomotion rather than 3D space. Although some wall transition methods have been proposed, they are specific to certain legged structures and have not been integrated into the navigation framework in full 3D environments. The planning of collision-free and accessible paths for legged climbing UGVs with any configuration in a 3D environment remains an open problem. This paper proposes a map representation suitable for the navigation planning of LC-UGVs in 3D space, named the Multi-Level Elevation Map (MLEM). Based on this map representation, we propose a universal hierarchical planning architecture. A global planner is applied to rapidly find cross-plane topological paths, and then a local planner and a motion generator based on motion primitives produces accessible paths and continuous motion trajectories. The hierarchical planning architecture equips the LC-UGVs with the ability to transition between different walls, thereby allowing them to navigate through challenging 3D environments. Full article

Humanoid robots are becoming a global research focus. Due to the limitations of bipedal walking technology, mobile humanoid robots equipped with a wheeled chassis and dual arms have emerged as the most suitable configuration for performing complex tasks in factory or home environments. To address the high redundancy issue arising from the wheeled chassis and dual-arm design of mobile humanoid robots, this study proposes a whole-body coordinated motion control algorithm based on arm potential energy optimization. By constructing a gravity potential energy model for the arms and a virtual torsional spring elastic potential energy model with the shoulder-wrist line as the rotation axis, we establish an optimization index function for the arms. A neural network with variable stiffness is introduced to fit the virtual torsional spring, representing the stiffness variation trend of the human arm. Additionally, a posture mapping method is employed to map the human arm potential energy model to the robot, enabling realistic humanoid movements. Combining task-space and joint-space planning algorithms, we designed experiments for single-arm manipulation, independent object retrieval, and dual-arm carrying in a simulation of a 23-degree-of-freedom mobile humanoid robot. The results validate the effectiveness of this approach, demonstrating smooth motion, the ability to maintain a low potential energy state, and conformity to the operational characteristics of the human arm. Full article

The purpose of this study was to ensure the compliance and safety of a robot’s movements during interactions with the external environment. This paper proposes a control strategy for learning variable impedance characteristics from multiple sets of demonstration trajectories. This strategy can adapt to the control of different joints by adjusting the parameters of the variable impedance control policy. Firstly, multiple sets of demonstration trajectories are aligned on the time axis using Dynamic Time Warping. Subsequently, the variance obtained through Gaussian Mixture Regression and a variable impedance strategy based on an improved Softplus function are employed to represent the variance as the variable impedance characteristic of the robotic arm, thereby enabling variable impedance control for the robotic arm. The experiments conducted on a self-designed robotic arm demonstrate that, compared to other variable impedance methods, the motion accuracy of the trajectories of joints 1 to 4 improved by 57.23%, 3.66%, 5.36%, and 20.16%, respectively. Additionally, a stiffness-variable segmented generalization method based on Dynamic Movement Primitive is proposed to achieve variable impedance control in various task environments. This strategy fulfills the requirements for compliance and safety during robot interactions. Full article

Programming by demonstration has shown potential in reducing the technical barriers to teaching complex skills to robots. Dynamic motion primitives (DMPs) are an efficient method of learning trajectories from individual demonstrations using second-order dynamic equations. They can be expanded using neural networks to learn longer and more complex skills. However, the length and complexity of a skill may come with trade-offs in terms of accuracy, the time required by experts, and task flexibility. This paper compares neural DMPs that learn from a full demonstration to those that learn from simpler sub-tasks for a pouring scenario in a framework that requires few demonstrations. While both methods were successful in completing the task, we find that the models trained using sub-tasks are more accurate and have more task flexibility but can require a larger investment from the human expert. Full article

Multi-agent pathfinding has been extensively studied by the robotics and artificial intelligence communities. The classical algorithm, conflict-based search (CBS), is widely used in various real-world applications due to its ability to solve large-scale conflict-free paths. However, classical CBS assumes discrete time–space planning and overlooks physical constraints in actual scenarios, making it unsuitable for direct application in unmanned aerial vehicle (UAV) swarm. Inspired by the decentralized planning and centralized conflict resolution ideas of CBS, we propose, for the first time, an optimal and efficient UAV swarm motion planner that integrates state lattice with CBS without any underlying assumption, named SL-CBS. SL-CBS is a two-layer search algorithm: (1) The low-level search utilizes an improved state lattice. We design emergency stop motion primitives to ensure complete UAV dynamics and handle spatio-temporal constraints from high-level conflicts. (2) The high-level algorithm defines comprehensive conflict types and proposes a motion primitive conflict detection method with linear time complexity based on Sturm’s theory. Additionally, our modified independence detection (ID) technique is applied to enable parallel conflict processing. We validate the planning capabilities of SL-CBS in classical scenarios and compare these with the latest state-of-the-art (SOTA) algorithms, showing great improvements in success rate, computation time, and flight time. Finally, we conduct large-scale tests to analyze the performance boundaries of SL-CBS+ID. Full article

This paper outlines a conceptual design for a multi-level natural language-based planning system and describes a demonstrator. The main goal of the demonstrator is to serve as a proof-of-concept by accomplishing end-to-end execution in a real-world environment, and showing a novel way of interfacing an LLM-based planner with open-set semantic maps. The target use-case is executing sequences of tabletop pick-and-place operations using an industrial robot arm and RGB-D camera. The demonstrator processes unstructured user prompts, produces high-level action plans, queries a map for object positions and grasp poses using open-set semantics, then uses the resulting outputs to parametrize and execute a sequence of action primitives. In this paper, the overall system structure, high-level planning using language models, low-level planning through action and motion primitives, as well as the implementation of two different environment modeling schemes—2.5 or fully 3-dimensional—are described in detail. The impacts of quantizing image embeddings on object recall are assessed and high-level planner performance is evaluated using a small reference scene data set. We observe that, for the simple constrained test command data set, the high-level planner is able to achieve a total success rate of 96.40%, while the semantic maps exhibit maximum recall rates of 94.69% and 92.29% for the 2.5d and 3d versions, respectively. Full article

This study presents an integrated system for object recognition, six-degrees-of-freedom pose estimation, and dexterous manipulation using a JACO robotic arm with an Intel RealSense D435 camera. This system is designed to automate the manipulation of industrial valves by capturing point clouds (PCs) from multiple perspectives to improve the accuracy of pose estimation. The object recognition module includes scene segmentation, geometric primitives recognition, model recognition, and a color-based clustering and integration approach enhanced by a dynamic cluster merging algorithm. Pose estimation is achieved using the random sample consensus algorithm, which predicts position and orientation. The system was tested within a 60° field of view, which extended in all directions in front of the object. The experimental results show that the system performs reliably within acceptable error thresholds for both position and orientation when the objects are within a ±15° range of the camera’s direct view. However, errors increased with more extreme object orientations and distances, particularly when estimating the orientation of ball valves. A zone-based dexterous manipulation strategy was developed to overcome these challenges, where the system adjusts the camera position for optimal conditions. This approach mitigates larger errors in difficult scenarios, enhancing overall system reliability. The key contributions of this research include a novel method for improving object recognition and pose estimation, a technique for increasing the accuracy of pose estimation, and the development of a robot motion model for dexterous manipulation in industrial settings. Full article

This paper introduces a swift method for intercepting the state trajectory of large-scale invading drone swarms using quadrotor drones. The research primarily concentrates on the design and computation of multi-target interception trajectories, with an analysis of the trajectory state constraints inherent to multi-target interception tasks. Utilizing Pontryagin’s principle of motion, we have designed computationally efficient motion primitives for multi-target interception scenarios. These motion primitives’ durations have informed the design of cost matrices for multi-target interception tasks. In contrast to static planar scenarios, the cost matrix in dynamic scenarios displays significant asymmetry, correlating with the speed and spatial distribution of the targets. We have proposed an algorithmic framework based on three genetic operators for solving multi-target interception trajectories, offering certain advantages in terms of solution accuracy and speed compared to other optimization algorithms. Simulation results from large-scale dynamic target interception scenarios indicate that for an interception task involving 50 targets, the average solution time for trajectories is a mere 3.7 s. Using the methods proposed in this paper, we conducted a comparative analysis of factors affecting the performance of interception trajectories in various target interception scenarios. This study represents the first instance in existing public research where precise evaluations have been made on the trajectories of drone interceptions against large-scale flying targets. This research lays the groundwork for further exploration into game-theoretic adversarial cluster interception methods. Full article