The whole-body control of mobile manipulators for the 6-DOF trajectory following task is the basis of many continuous tasks. However, traditional control strategies rely on accurate models and expert knowledge for solving the trajectory following task. Deep reinforcement learning (DRL) provides a promising model-free solution, but it is sample-inefficient. To this end, we propose Trajectory Following Hindsight Experience Replay (TF-HER), a sample-efficient DRL algorithm for the whole-body coupled trajectory following task with dense rewards. TF-HER builds a multi-trajectory state space, and relabels the low-reward data to generate informative high-reward experiences. Also, the distributional shift caused by the relabeling is corrected by estimating the density ratio of relabeled experiences. Extensive demonstrations on both nonholonomic and holonomic bases in simulation validate that our algorithm can accelerate the model convergence and significantly improve the sample efficiency. Furthermore, we present real-world experiments to demonstrate the effectiveness of our approach. The code is available: https://github.com/IRMV-Manipulation-Group/TF-HER.

This study presents a method for mobile manipulators to transport heavy and large objects by utilizing environmental support, thereby extending the capability of mobile manipulators to manipulate objects that exceed their payload capacity. This is a challenging task, as the agent must achieve whole-body coordination while satisfying multiple constraints, including payload limits, base collision avoidance, and joint limits for torque, velocity, and position. We propose a hierarchical deep reinforcement learning with model guidance to address the whole-body contact-rich mobile manipulation task. The system includes two main components: 1) high-level trajectory correction of end-effector based on dynamic movement primitives in operational space and 2) low-level redundancy resolution guided by a model-based safety filter, which filters out unsafe action and generates safe action by quadratic programming method. The proposed hierarchical structure can ensure the convergence of end-effector trajectory while solving the nonstationary transition problem during parallel training. Experiments in simulation and real-world show the system's effectiveness in achieving faster convergence, greater stability, and higher performance in mobile manipulation tasks compared to conventional methods.

This article explores a specialized problem of safely manipulating a moving object on a surface concerning moving obstacles with an industrial manipulator. To address this challenge, we formulate it as an optimal trajectory optimization problem to yield a safe, smooth, and locally time-optimal trajectory. Specifically, we propose a task-oriented trajectory planning algorithm that enables reaching and controlling a moving target on the surface as quickly as possible without specifying the reaching moment. Then we formally construct a spatiotemporal safe manifold to handle time-varying obstacles on the surface. The initially planned trajectory is projected onto this manifold, generating a safe but nonsmooth and time-consuming result. Finally, we leverage this result as an initial estimate for the optimization problem to efficiently generate a preferable trajectory while keeping the constraints not violated. Simulations and practical experiments in a production environment demonstrate the approaches presented. The results confirm the effectiveness of our algorithms, which offers an efficient solution to the challenge of manipulating a moving object on a surface.

Visual servoing is established as a theoretically reliable scheme for achieving high-precision robotic control. However, various image and physical constraints inevitably limit the application of visual servoing methods. This manuscript proposes a controller based on quadratic programming with proven local stability, explicitly handling some dominant constraints. Other difficult-to-model constraints, such as collisions, are addressed using an efficient sampling-based bidirectional planning framework designed for the visual servoing problem. Considering constraints, the proposed method explores the permissible image space by progressively expanding two search trees and ultimately generates feasible image trajectories. Subsequently, the quadratic programming-based local controller is extended to the tracking problem, aiming to track the planned trajectory and guide the manipulator to reach target features. The effectiveness of the proposed methods is demonstrated through various simulated and real experiments with a seven-degree-of-freedom manipulator. Comprehensive comparative experiments against several related methods highlight the performance of the proposed method.

In visual tracking, the tracking model must be updated online, which often leads to undesired inclusion of corrupted training samples, and hence inducing tracking failure. We present a locality preserving correlation filter (LPCF) integrating a novel and generic decontamination approach, which mitigates the model drift problem. Our decontamination approach maintains the local neighborhood feature points structures of the bounding box center. This proposed tracking-result validation approach models not only the spatial neighborhood relationship but also the topological structures of the bounding box center. Additionally, a closed-form solution to our approach is derived, which makes the tracking-result validation process could be accomplished in only milliseconds. Moreover, a dimensionality reduction strategy is introduced to improve the real-time performance of our translation estimation component. Comprehensive experiments are performed on OTB-2015, LASOT, TrackingNet. The experimental results show that our decontamination approach remarkably improves the overall performance by 6.2%, 12.6%, and 3%, meanwhile, our complete algorithm improves the baseline by 27.8%, 34.8%, and 15%. Finally, our tracker achieves the best performance among most existing decontamination trackers under the real-time requirement.

The rapid and accurate acquisition of crop planting spatial location information using remote sensing is one of the important guarantees to maintain the sustainable development of agriculture. However, the accuracy of crop identification by remote sensing is currently limited by many factors, such as the influence of other ground objects and the lack of time-series data. To overcome the above problems, this paper proposes an algorithm named improved artificial immune network crop recognition algorithm based on dispersed vegetation index genetic chain (IaiNet). This algorithm can be combined with multi-spectral data from Sentinel-2 series satellites for crop identification. As a test case, we identified and evaluated 3 different crop recognition scenarios in Henan, China. The results show that IaiNet can accurately identify the spatial distribution of crop planting. In all identification results, the accuracy is higher than 90%, and the kappa coefficient is greater than 0.9. In addition, the crop recognition results of IaiNet are significantly better than the random forest algorithm and support vector machine algorithm.