Humanoid robots are engineered to navigate terrains akin to those encountered by humans, which necessitates human-like locomotion and perceptual abilities. Currently, the most reliable controllers for humanoid motion rely exclusively on proprioception, a reliance that becomes both dangerous and unreliable when coping with rugged terrain. Although the integration of height maps into perception can enable proactive gait planning, robust utilization of this information remains a significant challenge, especially when exteroceptive perception is noisy. To surmount these challenges, we propose a solution based on a teacher-student distillation framework. In this paradigm, an oracle policy accesses noise-free data to establish an optimal reference policy, while the student policy not only imitates the teacher’s actions but also simultaneously trains a world model with a variational information bottleneck for sensor denoising and state estimation. Extensive evaluations demonstrate that our approach markedly enhances performance in scenarios characterized by unreliable terrain estimations. Moreover, we conducted rigorous testing in both challenging urban settings and off-road environments, the model successfully traverse 2 km of varied terrain without external intervention.

From the optimization perspective, this article proposes a novel actual shape-based obstacle avoidance synthesized by velocity–acceleration minimization (ASOA-VAM) scheme that performs operational tasks safely in a complex environment utilizing redundant manipulators. Concretely, an actual shape-based obstacle avoidance (ASOA) strategy with a variable magnitude escape acceleration using the Gilbert–Johnson–Keerthi distance algorithm is presented. Trajectory tracking, the end-effector’s errors feedback, and the joint multilevel physical limits (joint angle, -velocity, and -acceleration limits) avoidance are also incorporated into this optimization scheme. Meanwhile, the velocity–acceleration minimization (VAM) measure is developed. Combining the ASOA strategy with the VAM measure, the ASOA-VAM scheme is formed and further reformulated as a quadratic program (QP). Moreover, a recurrent neural network with theoretically provable convergence is designed to solve the QP online. Finally, simulations, comparisons, and experiments of a 7-degree-of-freedom manipulator with engineering applications illustrate the ASOA-VAM scheme’s effectiveness, accuracy, superiority, and physical realizability.

Edge detection is one of the most fundamental operations in the field of image analysis and computer vision as a critical preprocessing step for high-level tasks. It is difficult to give a generic threshold that works well on all images as the image contents are totally different. This paper presents an adaptive, robust and effective edge detector for real-time applications. According to the two-dimensional entropy, the images can be clarified into three groups, each attached with a reference percentage value based on the edge proportion statistics. Compared with the attached points along the gradient direction, anchor points were extracted with high probability to be edge pixels. Taking the segment direction into account, these points were then jointed into different edge segments, each of which was a clean, contiguous, 1-pixel wide chain of pixels. Experimental results indicate that the proposed edge detector outperforms the traditional edge following methods in terms of detection accuracy. Besides, the detection results can be used as the input information for post-processing applications in real-time.

This study presents a fast and robust ellipse detector based on edge following method. The detector first extracts segments using an edge predictor based on curvature analysis. Then, line segments are generated based on length condition other than least‐squares approximation. After that, potential ellipses are detected based on edge curvature and convexity. In addition, a re‐find contours detection method is introduced to improve the accuracy by searching edge points in the missing part of the ellipse. The performance of the detector has been tested on different datasets containing both synthetic and real images with three other algorithms based on the edge following method. Experimental results indicate that the proposed method always has the fastest execution time. Besides, it advances the state of the art in accuracy in most cases. Generally speaking, it is a fast, robust and effective ellipse detector for real‐time applications.

This paper is to develop an ontology-based mobile environment for collaborative product design and manufacture, which enables geographically dispersed team members to collaborate over the internet within the total design or manufacturing process, including product design specification, conceptual design, detail design, manufacture and recycling. In this paper, a database which based on a new method named ontology is built up to demonstrate the all related information in order to achieve an efficient and convenient management. According these two achievements, a new data management system is built and tested in the mobile device and compared to the traditional data management system at the end of this paper.

In order to eliminate the drawbacks of conventional force feedback gloves, a new type of master hand has been developed. By utilizing three ¿four-bar mechanism joint¿ in series and wire coupling mechanism, the master finger transmission ratio is kept exact 1:1.4:1 in the whole movement range and it can make active motions in both extension and flexion direction. Additionally, to assure faster data transmission and near zero delay in master-slave operation, a digital signal processing/field programmable gate array (DSP/FPGA-FPGA) structure with 200 ¿s cycle time is designed. The operating modes of the master hand can be contact or non-contact, which depends on the motion states of slave hand, free motion or constrained motion. The position control employed in non-contact mode ensures unconstrained motion and the force control adopted in contact mode guarantees natural contact sensation. To evaluate the performances of the master hand, an master-slave control experiment based on force-position control method between the master hand and DLR/HIT hand is conducted. The results demonstrate this new type master hand can augment telepresence.

This paper presents a DSP/FPGA based multi-sensory flexible-joint robot including modular mechanics, hardware and software architecture. The robot is composed of four modular flexible joints and a DLR-HIT-Hand. In each joint there is a Field Programmable Gate Array (FPGA) for sensor data processing, brushless DC motor control and communication. The kernel of the hardware system is a PCI-based high speed floating-point Digital Signal Processor (DSP) for the arm/hand Cartesian level control, and FPGA for two high speed (up to 25 Mbps) real-time Serial Buses communication with the arm and hand. All the electronics are integrated into the joint to achieve the high modularity and reliability. Cartesian impedance control and position control with on-line gravity compensation are realized for regulation tasks of the robot with elastic joints. In addition, the experiments of the joint impedance control and Cartesian impedance control demonstrate that the multi-sensors highly integrated robot has a good performance.

This paper gives an overview of the Chinese intelligent space robotic system. The system consists of a 6 DOF robot arm, a large-error tolerated gripper with two stereo cameras and onboard computer. The robot arm is composed of six identical modular joints, a big central hole in the modular joint was designed for the placement of the cables and plugs in the robot arm, which prevented them from damage of high temperature, radiation in the space environment and the motion of the robot. Joint torque sensor, joint position sensor and temperature sensors etc.., were integrated into the fully modular multi-sensory joint, which made the joint more intelligent. Also, a large-error tolerated gripper with two stereo cameras has been also designed to capture a microtarget satellite (MTS). A fault-tolerant onboard computer (OBC) with dual processing modules has been developed for the robot control. A zero gravity experimental system was developed to verify the functions of the robot arm under zero gravity environment

The cost and risks associated with the execution of robotics tasks in space require that all procedures be verified on Earth prior to their execution. The DLR-HIT Joint Robotics Lab is responsible for the verification of all the tasks of space manipulator of the Chinese free-flight robot space satellite system. We are currently developing the free-flight robot task verification facility (FTVF) through a hardware-in-the-loop way. It consists of a series of simulation and analysis tools to be used for verifying the kinematics (clearance, interface reach, degrees of freedom), dynamics (computed torque, flexibility), visual accessibility (ability to see the work site) and computation power (control period). This paper presents both theoretical and experimental study on the control of a free-flying robot manipulator for space application. The goal of the study is to develop a new control method and hardware-in-the-loop simulation system for target capturing with vision sensor in micro-gravity space environment, considering the dynamical interaction between the space robot and its mobile satellite base. Finally experimental results demonstrate the effect of the simulation system

A new five-fingered underactuated prosthetic hand control system is presented in this paper. The prosthetic hand control part is based on an EMG motion pattern classifier which combines VLR (variable learning rate) based neural network with wavelet transform and sample entropy. This motion pattern classifier can successfully identify flexion and extension of the thumb, the index finger and the middle finger, by measuring the surface EMG signals through three electrodes mounted on the flexor digitorum profundus, flexor pollicis longus and extensor digitorum. Furthermore, via continuously controlling single finger's motion, the prosthetic hand can achieve more prehensile postures such as power grasp, fingertip grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its high recognition capability

This paper presents a surface Electromyography (EMG) motion pattern classifier which combines Levenberg-Marquardt (LM) based neural network with parametric Autoregressive (AR) model. This motion pattern classifier can successfully identify three types of motion of thumb, index finger and middle finger, by measuring the surface EMG through two electrodes mounted on the flexor digitorum profundus and flexor pollicis longus. Furthermore, via continuously controlling single finger’s motion, the five-fingered underactuated prosthetic hand can achieve more prehensile postures such as power grasp, centralized grip, fingertip grasp, cylindrical grasp, etc. The experimental results show that the classifier has a great potential application to the control of bionic man-machine systems because of its fast learning speed, high recognition capability and strong robustness.

This paper presents the current work progress of HIT/DLR Dexterous Hand. Based on the technology of DLR Hand II, HIT and DLR are jointly developing a smaller and easier manufactured robot hand. The prototype of one finger has been successfully built. The finger has three DOF and four joints, the last two joints are mechanically coupled by a rigid linkage. All the actuators are commercial brushless DC motors with integrated analog Hall sensors. DSP based control system is implemented in PCI bus architecture and the serial communication between the hand and DSP needs only 6 lines(4 lines power supply and 2 lines communication interface). The fingertip force can reach 10N.