This paper presents an online multi-population evolution path planning (OMEPP) algorithm to address the flexible path planning problem for mobile manipulators in complex dynamic environments. The OMEPP algorithm treats the mobile manipulator as a high-dimensional system to utilize its flexibility. The OMEPP algorithm is based on random sampling and evolutionary concepts: Optimization and passive obstacle avoidance operations are performed on the path at runtime, with superior paths replacing inferior ones within the same population. A novel path population partitioning approach is proposed to maintain diverse switchable paths, thereby improving robustness. This paper also proposes an efficient manipulator collision detection method and several other mechanisms to enhance the algorithm’s effectiveness. The experimental results demonstrate the algorithm’s ability to swiftly adapt and optimize paths in response to dynamic environmental changes. Note to Practitioners—This paper presents OMEPP, an online evolutionary algorithm for real-time path planning of mobile manipulators in dynamic environments. OMEPP employs novel techniques including path population partitioning, random sampling, and evolution to efficiently generate collision-free paths among moving obstacles. A novel path population partitioning approach is proposed to maintain diverse switchable paths, thereby improving robustness. Simulations have demonstrated that the OMEPP algorithm is effective for real-time path planning of mobile manipulators in complex dynamic environments. Future work will focus on trajectory generation respecting dynamics limits.

In complex unstructured environments, accurate terrain traversability analysis is a fundamental requirement for the successful execution of any movements of ground robots, especially given that terrain traversability often exhibits anisotropy. However, the difficulty in obtaining multi-directional terrain labels hinders the emergence of end-to-end multi-directional traversability network. This paper introduces a framework for real-time multi-directional traversability maps (MTraMap) generation tailored for unstructured environments. It involves pre-training a uni-directional traversability classifier, termed UniTraT, through self-supervised learning using ground robot travel simulation. Furthermore, it employs Uni-directional to Multi-directional Traversability Distillation (UMTraDistill) to distill a multi-directional traversability network, termed MultiTCNN, which is capable of directly generating MTraMap. We evaluated both networks on our traversability dataset, achieving an 89% accuracy in terrain traversability classification with the UniTraT. Compared to UniTraT, the accuracy of the MultiTCNN distilled via UMTraDistill only decreases by 1.8%, and it can process 10 m × 10 m elevation map at a speed of 74 fps. Field robotics experiments were also conducted and showed that MultiTCNN can generate MTraMap of the surrounding 20 m × 20 m environment at a rate of 9.39 fps, with a slight reduction of 0.61 fps compared to the lidar data publishing rate, and the generated MTraMap can clearly delineate the multi-directional traversability of the surrounding environments.

The quality of a robot’s environmental perception determines whether it can achieve more intelligent applications, such as semantic interaction with humans. SLAM, on the other hand, is one of the crucial capabilities for a robot to perceive its environment. However, when only a monocular image is provided, dynamic objects in the environment significantly impact the accuracy of map construction by the robot, leading to erroneous perception results. To address this issue, we propose a Visual SLAM framework based on BEV perception results, named BE-SLAM. With this framework, we can handle dynamic objects, occlusions, and incompletely observed objects. It can construct a stable static map by strengthening trust in static objects. Considering that object-level semantic maps can enhance a robot’s perception abilities, we also reconstruct static objects in the map and use them to optimize the pose. Through experiments on existing publicly available dataset, we compare BE-SLAM with several existing methods that have shown good performance. The experimental results demonstrate that BE-SLAM performs exceptionally well on high-dynamic sequences and achieves comparable results on static or low-dynamic sequences.

Ball screw feed-drive system (BSFDS) is a widely used high-precision positioning mechanism, and its positioning accuracy is strongly limited by friction, vibration, etc. Those factors are difficult to model or to model completely. Since the data-driven control approach is not model dependent, it is suitable to overcome the previous problems. Iterative learning control (ILC) is one of the general unfixed-structure data-driven approaches, but it is restricted by its residual error. Therefore, this article proposes a combined unfixed-structure and fixed-structure data-driven feedforward control method. Notably, the unfixed-structure part adopts a standard norm-optimal ILC, and the fixed-structure part is a finite impulse response (FIR) filter structure. Then, the corresponding optimization algorithms are proposed to design an unfixed-structure ILC feedforward controller and to optimize the parameters of the fixed-structure FIR feedforward controller. Furthermore, the convergence and trajectory tracking performances of the proposed method are analyzed. The proposed data-driven feedforward control strategy is experimentally validated and compared with a preexisting FIR approach and standard norm-optimal ILC. The results show that the proposed approach has better convergence performance and trajectory tracking performance, and represents an effective strategy to improve the positioning accuracy in BSFDS.

Diagnosis of a civil aircraft engine, which is operating under speed variation conditions, is a representative problem encountered in aeronautic industry. It is still very challenging to estimate the instantaneous angular speed (IAS) through the aircraft engine vibration signal when no encoder or tachometer is available due to cost or technological reasons. However, for the currently available tacholess order tracking algorithms, many vital parameters must be initialized manually in advance, which lead to user-friendliness, even false diagnosis. To address this issue, a novel method is proposed and the merits of nonlinear mode decomposition are inherited, so the IAS can be estimated adaptively without prior knowledge. The vibration signal collected from a civil aircraft engine is used for validation; the experimental results exhibit that the proposed method is more accurate and flexible when compared with the conventional methods.