Achieving robust locomotion on complex terrains remains a challenge due to high-dimensional control and environmental uncertainties. This paper introduces a teacher-prior framework based on the teacher-student paradigm, integrating imitation and auxiliary task learning to improve learning efficiency and generalization. Unlike traditional paradigms that strongly rely on encoder-based state embeddings, our framework decouples the network design, simplifying the policy network and deployment. A high-performance teacher policy is first trained using privileged information to acquire generalizable motion skills. The teacher’s motion distribution is transferred to the student policy, which relies only on noisy proprioceptive data, via a generative adversarial mechanism to mitigate performance degradation caused by distributional shifts. Additionally, auxiliary task learning enhances the student policy’s feature representation, speeding up convergence and improving adaptability to varying terrains. The framework is validated on a humanoid robot, showing a great improvement in locomotion stability on dynamic terrains and significant reductions in development costs. This work provides a practical solution for deploying robust locomotion strategies in humanoid robots.

Benefiting from its hyper-redundant structure, the biomimetic snake-like manipulator retains its remarkable flexibility even within confined spaces. However, its motion planning and control pose significant challenges. This paper imitates the winding uncoiling behavior of snakes to achieve controllable constrained path following. Firstly, based on control points, a recursive computational model and an equivalent planning angle model are established, enabling efficient and analytical determination of joint positions, collision regions, and motion parameters during the path following. Subsequently, the sliding control point algorithm and motion smoothing restriction algorithm are designed. The former ensures that the remaining segments during following strictly remain within the collision-free regions defined by the base and path controls, while the latter smooths the control parameters based on velocity and acceleration limitations. Finally, simulation and practical experiments demonstrate the feasibility of the proposed methods. The prototype that applied our method can reach targets and accomplish tasks, further validating the applicability of the snake-like manipulator.

Cable-driven hyper-redundant manipulators (CDHRMs) enable unique tasks in confined spaces while presenting challenges for collision-free path planning. This article introduces a novel planning method called the stepwise follow-the-leader (SFTL) algorithm. SFTL consists of a local planner and a global planner. The local planner utilizes reinforcement learning to obtain a collision-free policy, optimizing target error, path length, angle fluctuation, and TE. The global planner incorporates an observation tree and reachability estimator to dynamically optimize extended path nodes for the local planner. The proposed sliding control points algorithm enables sequential movement along the planned path. The SFTL algorithm is applied to a coiled CDHRM and validated through simulations and practical experiments. Results show an average success rate of over 96% in various scenes, maintaining appropriate joint angles and cable tension. SFTL generates sensor-informed feasible paths, providing a robust planning framework for industrial CDHRM applications.

Operating in narrow spaces is an important challenge in the development of robots. Redundant manipulators are one way to solve this problem, but their mechanism design and control method still have much room for improvement. In this paper, we propose a coiled cable-conduit-driven hyper-redundant manipulator (C-CDHRM) with great slenderness and flexibility. In terms of mechanism design, it considers both compactness and operability. By imitating the structure and behavior of a constricting snake, it can be uncoiled sequentially from a coiled storage state, led by the head. In terms of control methods, we propose a multi-layer control system that can make remote operations more accurate and reliable. On the one hand, guiding, segmenting, and following the path overcome the planning ambiguity caused by redundancy. On the other hand, conduit transmission modeling and cable length correction overcome the nonlinear mapping of cable-driven joints and were verified in experiments. Through tests, the mobile integrated system composed of C-CDHRM has an excellent performance in operation precision and accuracy, ensuring safety and accessibility in narrow spaces. Finally, in field experiments, the inspection and cleaning of various types of electrical equipment have been successfully completed, showing excellent application prospects.

Abstract The application of traditional 3D reconstruction methods such as structure-from-motion and simultaneous localization and mapping are typically limited by illumination conditions, surface textures, and wide baseline viewpoints in the field of robotics. To solve this problem, many researchers have applied learning-based methods with convolutional neural network architectures. However, simply utilizing convolutional neural networks without taking other measures into account is computationally intensive, and the results are not satisfying. In this study, to obtain the most informative images for reconstruction, we introduce a residual block to a 2D encoder for improved feature extraction, and propose an attentive latent unit that makes it possible to select the most informative image being fed into the network rather than choosing one at random. The recurrent visual attentive network is injected into the auto-encoder network using reinforcement learning. The recurrent visual attentive network pays more attention to useful images, and the agent will quickly predict the 3D volume. This model is evaluated based on both single- and multi-view reconstructions. The experiment results show that the recurrent visual attentive network increases prediction performance in a way that is superior to other alternative methods, and our model has desirable capacity for generalization.

The hybrid-structured flexible manipulator has a complex structure and strong coupling between state variables. Meanwhile, the natural frequency of the hybrid-structured flexible manipulator varies with the motion of the telescopic joint, so it is difficult to suppress the vibration quickly. In this article, the tip state signal of the hybrid-structured flexible manipulator is decomposed into elastic vibration signal and tip vibration equilibrium position signal, and a combined control method is proposed to improve tip positioning accuracy and trajectory tracking accuracy. In the proposed combined control method, an improved nominal model-based sliding mode controller (NMBSMC) is used as the main controller to output the driving torque, and an actor-critic-based reinforcement learning controller (ACBRLC) is used as an auxiliary controller to output small compensation torque. The improved NMBSMC can be divided into a nominal model-based sliding mode robust controller and a practical model-based integral sliding mode controller. Two sliding mode controllers with different structures make full use of the mathematical model and the measured data of the actual system to improve the vibration equilibrium position tracking accuracy. The ACBRLC uses the tip elastic vibration signal and the prioritized experience replay method to obtain the small reverse compensation torque, which is superimposed with the output of the NMBSMC to suppress tip vibration and improve the positioning accuracy of the hybrid-structured flexible manipulator. Finally, several groups of experiments are designed to verify the effectiveness and robustness of the proposed combined control method.

Producing a 3D voxel from a single view by deep learning-based methods has garnered increasing attention. Several state-of-the-art works introduce the recurrent neural network(RNN) to fuse features and generate full volumetric occupancy. However, the inputs are unable to be fully exploited to improve the reconstruction due to long-term memory loss. And most of the works have considered using 3D supervision for the whole optimization to recover the full volume, but lack detailed silhouette supervision to refine the reconstruction process. To address these issues, an end-to-end object reconstruction network with scaling volume-view supervision is proposed. We introduce an auto-encoder 3D volume predicting network that takes a single arbitrary image as input and outputs a voxel occupancy grid. And a scaling volume-view supervision module, which uses up-sampling to zoom errors and increase penalties, is leveraged to improve both the global and local optimization. Extensive experimental analysis on ShapeNet dataset shows that our network has superior performance when the scaling volumeview supervision is involved and the deep residual module boosts the reconstruction performance and speeds up the optimization effectively.