This paper proposes a novel mathematical solution to solve the inverse kinematics (IK) of single section mobile continuum manipulators (SSMCMs). Thus, to achieve a given pose of the end-effector (EE), the proposed mathematical solution consists in determining the position and orientation parameters of the mobile platform and of a single section of the continuum manipulator. As advantages, the proposed mathematical solution eliminates the EE pose errors when the dynamic parameters are neglected and the continuum manipulator is cylindrical in shape. A simulation and an experiment validate the proposed approach.

The task space control of robot manipulators requires solving the thorny problem of stabilizing the compound system {outer controller - inner controller - robot manipulator}. To stabilize this compound system, both controllers must be designed by the user to achieve convergence of the tracking error. This problem is tricky to solve in the case of the control of an industrial robot manipulator because its internal controller is not accessible to users. In this work, we propose an adaptive neural network outer controller. The neural networks approximate the dynamics of the inner controller, the kinematic and dynamic parameters of the robot. Besides, the adaptive part finds parameters that achieve the stability of the global system. Since an adaptive approach is sensitive to errors in initial values, we have integrated into the controller a term that constrains the closed-loop system to maintain the prescribed performances. The effectiveness of the approach is demonstrated through Lyapunov's theory, simulation comparisons, and experimental studies.

In this work, an energy planning strategy is proposed for over-actuated unmanned road vehicles (URVs) having redundant steering configurations. In fact, indicators on the road geometry, the actuation redundancy, the optimal velocity profile, and the driving mode are evaluated for each segment of the URV's trajectory. To reach this objective, a power consumption estimation model is developed for the URV. Due to the presence of unknown dynamic parameters of the URV and uncertainties about its interaction with the environment, an artificial intelligence (AI) technique, based on data-learning qualitative method, is used for the power consumption estimation, namely Adaptive Neuro Fuzzy Inference System (ANFIS). The ANFIS model is obtained using trained data from a Real URV dynamics. Then, an energy digraph is built with all feasible configurations taking into account the kinematic and dynamic constraints based on a 3D grid map setup, according to velocity, arc-length, and driving mode. In this weighted directed graph, the edges describe the consumed energy by the URV along a segment of a trajectory. The vertices describe the start and end points of each segment. Subsequently, an optimization algorithm is applied on the digraph to get a global optimal solution combining driving mode, power consumption, and velocity profile of the URV. The obtained results are compared with the dynamic programming method for global offline optimization. Finally, the obtained simulation and experimental results, applied on RobuCar URV, highlight the effectiveness of the proposed energy planning.

Soft robotics is a swiftly growing research area these days. Modeling continuum robots accurately is still a demanding field. The paper aims to propose a shape reconstruction method and the estimation of the kinematic behavior of heterogeneous continuum robot in closed loop kinematic configuration, by using Pythagorean Hodograph (PH) curves. The validation of the model approach has been tested on cooperative continuum robots, namely Compact Bionic Handling Arms (CBHA), driving an intermediate flexible rope (a passive flexible link), by using a 3D tracking system. Experimental comparison of the proposed approach with the existing approaches is performed in terms of accuracy as well as the time cost.

This paper addresses the position control of continuum manipulators. Their performances in terms of speed limitation and position accuracy are often mediocre compared with rigid body based robots. In regards to continuum manipulators control, nonadaptive kinematic schemes were shown poor performance in terms of tracking position accuracy, and existing adaptive schemes were time-consuming. This paper presents a novel adaptive control scheme, namely the adaptive support vector regressor controller. The proposed approach exploits the optimization learning methods which yield global solutions of the training problem while keeping small size regressors. These characteristics make it possible to accelerate the convergence of the closed-loop system, thus reducing the execution time. The experimental results obtained using the compact bionic handling assistant robot demonstrate that nonadaptive kinematic architectures even in the presence of accurate learning models are not robust enough to deal with these challenging platforms and that adaptive control schemes can significantly improve the performance.

Compact Bionic Handling Assistant (CBHA) is a continuum manipulator, with pneumatic-based actuation and compliant gripper. This bionic arm is attached to a mobile robot named Robotino. Inspired by the elephant's trunk, it can reproduce biological behaviors of trunks, tentacles, or snakes. Unlike rigid link robot manipulators, the development of high performance control algorithm of continuum robot manipulators remains a challenge, particularly due to their complex mechanical design, hyper-redundancy and presence of uncertainties. Numerous studies have been investigated for modeling of such complex systems. Such continuum robots, like the CBHA present a set of nonlinearities and uncertainties, making difficult to build an accurate analytical model, which can be used for control strategies development. Hence, learning approach becomes a suitable tool in such scenarios in order to capture un-modeled nonlinear behaviors of the continuous robots. In this paper, we present a qualitative modeling approach, based on neuronal model of the inverse kinematic of CBHA. A penalty term constraint is added to the inverse objective function into Distal Supervised Learning (DSL) scheme to select one particular inverse model from the redundancy manifold. The inverse kinematic neuronal model is validated by conducting a real-time implementation on a CBHA trunk.