Autonomous, flexible, and human–robot collaboration are the key features of the next-generation robot. Such unstructured and dynamic environments bring great challenges in online adaptive path planning. The robots have to avoid dynamic obstacles and follow the original task path as much as possible. A robust and efficient online path planning method is required accordingly. A method based on the Gaussian Mixture Model (GMM), Gaussian Mixture Regression (GMR), and the Probabilistic Roadmap (PRM) is proposed to overcome the above difficulties. During the offline stage, the GMM was used to model teaching data, and it can represent the offline-demonstrated motion and constraints. The optimal solution was encoded in the mean value, while the environmental constraints were encoded in the variance value. The GMR generated a smooth path with variance as the resample space according to the GMM of the teaching data. This representation isolated the old environment model with the novel obstacle. During the online stage, a Modified Probabilistic Roadmap (MPRM) was used to plan the motion locally. Because the GMM provides the distribution of all the feasible motion, the sampling space of the MPRM was generated by the variable density resampling method, and then, the roadmap was constructed according to the Euclidean and Probability Distance (EPD). The Dijkstra algorithm was used to search for the feasible path between the starting point and the target point. Finally, shortcut pruning and B-spline interpolation were used to generate a smooth path. During the simulation experiment, two obstacles were added to the recurrent scene to indicate the difference from the teaching scene, and the GMM/GMR-MPRM algorithm was used for path planning. The result showed that it can still plan a feasible path when the recurrent scene is not the same as the teaching scene. Finally, the effectiveness of the algorithm was verified on the IRB1200 robot experiment platform.

Soft manipulators can perform continuous operations due to their inherent compliance and dexterity, thus enabling safe interactions and smooth movements in confined environments. However, high compliance usually means low load capacity. It is important for a soft manipulator to possess proper flexibility while maintaining an acceptable stiffness to widen its applications. This paper has hence devoted efforts to a kind of variable stiffness mechanism for a soft manipulator actuated by pneumatic artificial muscles (PAMs). Due to the combination of contractile and extensor PAMs, the manipulator is able to vary its stiffness independently from the configuration. The stiffness characteristics of the soft manipulator are quantitatively analyzed by bending shape prediction under different loading and inflation conditions, and the prediction is built upon a nonlinear statics model coupled with PAM nonlinearity and the Cosserat theory. In addition, experimental measurements are conducted to further validate the expected performance of the manipulator design. The experimental and verified theoretical analysis results indicate that the manipulator shape and stiffness are greatly affected by the pressure variation of PAMs, realizing a large bending space with a high output force. The variable stiffness design obviously increases the manipulator’s ability to resist additional interference at the same position.

Hysteresis poses a significant challenge for the modelling and control of smart material-based actuators. The Prandtl-Ishlinskii (PI) operator-based model has been a popular choice for characterising the symmetric hysteresis properties of piezoceramic actuators. Various modified PI operators have also been suggested to extend the modelling technique to (a) asymmetric hysteresis and (b) input rate dependent hysteresis characteristics. A major advantage of using PI or modified PI operators is that they have an analytical inverse which allows the straightforward implementation of the inverse model to provide hysteresis compensation as part of a control scheme. The generalised PI operator, a type of modified PI operator, has the potential to model both asymmetric and constrained hysteresis characteristics. In this contribution the ability of the generalized PI operator-based model to approximate the hysteresis characteristics of two smart actuators; a tubular Dielectric Elastomer (DE) actuator with both saturated and unsaturated asymmetric hysteresis behaviour, and a Magnetorheological (MR) Damper with saturated and approximately symmetric hysteresis behaviour is investigated.