Learning Inverse Statics Models Efficiently With Symmetry-Based Exploration

Learning (inverse) kinematics and dynamics models of dexterous robots for the entire action or observation space is challenging and costly. Sampling the entire space is usually intractable in terms of time, tear, and wear. We propose an efficient approach to learn inverse statics models—primarily for gravity compensation—by exploring only a small part of the configuration space and exploiting the symmetry properties of the inverse statics mapping. In particular, there exist symmetric configurations that require the same absolute motor torques to be maintained. We show that those symmetric configurations can be discovered, the functional relations between them can be successfully learned and exploited to generate multiple training samples from one sampled configuration-torque pair. This strategy drastically reduces the number of samples required for learning inverse statics models. Moreover, we demonstrate that exploiting symmetries for learning inverse statics models is a generally applicable strategy for online and offline learning algorithms. We exemplify this by two different learning approaches. First, we modify the Direction Sampling approach for learning inverse statics models online, in a plain exploratory fashion, from scratch and without using a closed-loop controller. Second, we show that inverse statics mappings can be efficiently learned offline utilizing lattice sampling. Results for a 2R planar robot and a 3R simplified human arm demonstrate that their inverse statics mappings can be learned successfully for the entire configuration space. Furthermore, we demonstrate that the number of samples required for learning inverse statics mappings for 2R and 3R manipulators can be reduced at least by factors of approximately 8 and 16, respectively–depending on the number of discovered symmetries.

Modified Primal-Dual Neural Networks for Motion Control of Redundant Manipulators With Dynamic Rejection of Harmonic Noises

In recent decades, primal-dual neural networks, as a special type of recurrent neural networks, have received great success in real-time manipulator control. However, noises are usually ignored when neural controllers are designed based on them, and thus, they may fail to perform well in the presence of intensive noises. Harmonic noises widely exist in real applications and can severely affect the control accuracy. This work proposes a novel primal-dual neural network design that directly takes noise control into account. By taking advantage of the fact that the unknown amplitude and phase information of a harmonic signal can be eliminated from its dynamics, our deliberately designed neural controller is able to reach the accurate tracking of reference trajectories in a noisy environment. Theoretical analysis and extensive simulations show that the proposed controller stabilizes the control system polluted by harmonic noises and converges the position tracking error to zero. Comparisons show that our proposed solution consistently and significantly outperforms the existing primal-dual neural solutions as well as feedforward neural one and adaptive neural one for redundancy resolution of manipulators.

Estimation-Based Control of a Magnetic Endoscope without Device Localization

Magnetically controlled catheters and endoscopes can improve minimally invasive procedures as a result of their increased maneuverability when combined with modern magnetic steering systems. However, such systems have two distinct shortcomings: they require continuous information about the location of the instrument inside the human body and they rely on models that accurately capture the device behavior, which are difficult to obtain in realistic settings. To address both of these issues, we propose a control algorithm that continuously estimates a magnetic endoscope’s response to changes in the actuating magnetic field. Experiments in a structured visual environment show that the control method is able to follow image-based trajectories under different initial conditions with an average control error that measures 1.8 % of the trajectory length. The usefulness for medical procedures is demonstrated with a bronchoscopic inspection task. In a proof-of-concept study, a custom 2[Formula: see text]mm diameter miniature camera endoscope is navigated through an anatomically correct lung phantom in a clinician-controlled manner. This represents the first demonstration of the controlled manipulation of a magnetic device without localization, which is critical for a wide range of medical procedures.

Nonparametric Online Learning Control for Soft Continuum Robot: An Enabling Technique for Effective Endoscopic Navigation

Bioinspired robotic structures comprising soft actuation units have attracted increasing research interest. Taking advantage of its inherent compliance, soft robots can assure safe interaction with external environments, provided that precise and effective manipulation could be achieved. Endoscopy is a typical application. However, previous model-based control approaches often require simplified geometric assumptions on the soft manipulator, but which could be very inaccurate in the presence of unmodeled external interaction forces. In this study, we propose a generic control framework based on nonparametric and online, as well as local, training to learn the inverse model directly, without prior knowledge of the robot's structural parameters. Detailed experimental evaluation was conducted on a soft robot prototype with control redundancy, performing trajectory tracking in dynamically constrained environments. Advanced element formulation of finite element analysis is employed to initialize the control policy, hence eliminating the need for random exploration in the robot's workspace. The proposed control framework enabled a soft fluid-driven continuum robot to follow a 3D trajectory precisely, even under dynamic external disturbance. Such enhanced control accuracy and adaptability would facilitate effective endoscopic navigation in complex and changing environments.

Research on the operational reliability system control methodology and its application for aerospace mechanism

According to the characteristics of space missions and space environment, to slow performance deterioration and possible reliability attenuation for aerospace mechanisms, an operational reliability system control methodology is proposed in this article. A space manipulator – a kind of typical complicated aerospace mechanism – is chosen as the research object. First, considering relevant materials and structure mechanism of joint and link parts, the influence factors of operational reliability for space manipulator are divided. Then, by introducing the responding layer factors, a mapping relationship between the influence factors of operational reliability and control variables is analysed. On this basis, a new method to build a hierarchical control system of operational reliability for the aerospace mechanisms is proposed. In this method, the mechanism how the influence factors of operational reliability are introduced into the control system is defined, and an operational reliability system control model is built, which is made up of task planning, path planning, and motion control. Finally, the proposed methodology is further explained with the operational stability of a space manipulator as an example. After analysing the mapping relationship among the influence factors of operational reliability, the factors of responding layer and control variables, a multi-objective optimization method based on Nondominated Sorting Genetic Algorithm II (NSGA-II) is proposed to ensure the operation stability for a space manipulator. These optimization objectives are introduced into the optimized control model at path planning level as constraints. According to these constraints, the optimized control system can be adjusted to improve the operation stability of the manipulator, and the operational reliability is also improved during this process correspondingly. Simulation results prove the effectiveness of the proposed method.