Many human manipulation skills are force relevant, such as opening a bottle cap and assembling furniture. However, it is still a difficult task to endow a robot with these skills, which largely is due to the complexity of the representation and planning of these skills. This paper presents a learning-based approach of transferring force-relevant skills from human demonstration to a robot. First, the force-relevant skill is encapsulated as a statistical model where the key parameters are learned from the demonstrated data (motion, force). Second, based on the learned skill model, a task planner is devised which specifies the motion and/or the force profile for a given manipulation task. Finally, the learned skill model is further integrated with an adaptive controller that offers task-consistent force adaptation during online executions. The effectiveness of the proposed approach is validated with two experiments, i.e., an object polishing task and a peg-in-hole assembly.

Mapping operator motions to a robot is a key problem in teleoperation. Due to differences between workspaces, such as object locations, it is particularly challenging to derive smooth motion mappings that fulfill different goals (e.g. picking objects with different poses on the two sides or passing through key points). Indeed, most state-of-the-art methods rely on mode switches, leading to a discontinuous, lowtransparency experience. In this paper, we propose a unified formulation for position, orientation and velocity mappings based on the poses of objects of interest in the operator and robot workspaces. We apply it in the context of bilateral teleoperation. Two possible implementations to achieve the proposed mappings are studied: an iterative approach based on locallyweighted translations and rotations, and a neural network approach. Evaluations are conducted both in simulation and using two torque-controlled Franka Emika Panda robots. Our results show that, despite longer training times, the neural network approach provides faster mapping evaluations and lower interaction forces for the operator, which are crucial for continuous, real-time teleoperation.

The monocular visual odometer is widely used in the navigation of robots and vehicles, but it has defects of the unknown scale of the estimated trajectory. In this paper, we presented a position and attitude estimation method, integrating the visual odometer and Global Position System (GPS), where the GPS positioning results were taken as a reference to minimize the trajectory estimation error of visual odometer and derive the attitude of the vehicle. Hardware-in-the-loop simulations were carried out; the experimental results showed that the positioning error of the proposed method was less than 1 m, and the accuracy and robustness of the attitude estimation results were better than those of the state-of-art vision-based attitude estimation methods.

Environmentally friendly nonwoven fabrics can be formed through thermal bonding of cotton and cellulose acetate fiber blends at reduced bonding temperature with the aid of a plasticizer. Water has been introduced as an external plasticizer to lower the softening temperature of cellulose acetate fibers and to enhance the tensile strength of cotton/cellulose acetate web. It has been found that water can significantly increase the tensile strength of cotton/cellulose acetate thermally-bonded webs at reasonable bonding temperatures. In addition, water can enhance web bonding to essentially the same degree as an acetone treatment does. The mechanisms of water effect are considered and optimal processing conditions are proposed.

A half tracked vehicle model was established based on LMS, a co-simulation interface between control algorithm of MATLAB and physical model of LMS was set up. Fuzzy controller with PID regulator was proposed to achieve controlling strategy based on half tracked vehicle model. With suspension stroke and its change rate as input parameters of fuzzy controller, the dynamic adjusting parameters of PID controller are acquired through fuzzy controller, then a semi-active suspension vehicle adaptive control system was formed. The simulation result shows that the adaptive control system can effectively coordinate the contradiction acceleration and dynamic travel in different bands, the ride comfort tracked vehicle is significantly improved.