Perception-Action Coupling Target Tracking Control for a Snake Robot via Reinforcement Learning

Visual-guided locomotion for snake-like robots is a challenging task, since it involves not only the complex body undulation with many joints, but also a joint pipeline that connects the vision and the locomotion. Meanwhile, it is usually difficult to jointly coordinate these two separate sub-tasks as this requires time-consuming and trial-and-error tuning. In this paper, we introduce a novel approach for solving target tracking tasks for a snake-like robot as a whole using a model-free reinforcement learning (RL) algorithm. This RL-based controller directly maps the visual observations to the joint positions of the snake-like robot in an end-to-end fashion instead of dividing the process into a series of sub-tasks. With a novel customized reward function, our RL controller is trained in a dynamically changing track scenario. The controller is evaluated in four different tracking scenarios and the results show excellent adaptive locomotion ability to the unpredictable behavior of the target. Meanwhile, the results also prove that the RL-based controller outperforms the traditional model-based controller in terms of tracking accuracy.

Towards bio-inspired robots for underground and surface exploration in planetary environments: An overview and novel developments inspired in sand-swimmers

Dessert organisms like sandfish lizards (SLs) bend and generate thrust in granular mediums to scape heat and hunt for prey [1]. Further, SLs seems to have striking capabilities to swim in undulatory form keeping the same wavelength even in terrains with different volumetric densities, hence behaving as rigid bodies. This paper tries to recommend new research directions for planetary robotics, adapting principles of sand swimmers for improving robustness of surface exploration robots. First, we summarize previous efforts on bio-inspired hardware developed for granular terrains and accessing complex geological features. Later, a rigid wheel design has been proposed to imitate SLs locomotion capabilities. In order to derive the force models to predict performance of such bio-inspired mobility system, different approaches as RFT (Resistive Force Theory) and analytical terramechanics are introduced. Even in typical wheeled robots the slip and sinkage increase with time, the new design intends to imitate traversability capabilities of SLs, that seem to keep the same slip while displacing at subsurface levels.

Driving Mechanisms, Motion, and Mechanics of Screw Drive In-Pipe Robots: A Review

In recent years, interest in in-pipe robot research has been steadily increasing. This phenomenon reflects the necessity and urgency of pipe inspection and rehabilitation as several pipe networks have become outdated around the globe. In-pipe robots can be divided into several groups in accordance with their locomotion principles, each with its own advantages and best suited application scope. Research on the screw drive in-pipe robot (SDIR) has had a rising trend due to the robot’s simple driving mechanism design and numerous advantages. This study compares and analyzes the characteristics of various SDIRs from the aspects of mechanism design, driving principle, and motion and mechanical behaviors. Each SDIR has its own advantages and disadvantages depending on its design requirements and intended applications. A number of prototypes have been fabricated to verify their functionality and efficiency in inspection tasks. This study can provide an up-to-date reference for researchers to conduct further analysis on SDIRs.

Robust Neuro-Optimal Control of Underactuated Snake Robots With Experience Replay

In this paper, the problem of path following for underactuated snake robots is investigated by using approximate dynamic programming and neural networks (NNs). The lateral undulatory gait of a snake robot is stabilized in a virtual holonomic constraint manifold through a partial feedback linearizing control law. Based on a dynamic compensator and Line-of-Sight guidance law, the path-following problem is transformed to a regulation problem of a nonlinear system with uncertainties. Subsequently, it is solved by an infinite horizon optimal control scheme using a single critic NN. A novel fluctuating learning algorithm is derived to approximate the associated cost function online and relax the initial stabilizing control requirement. The approximate optimal control input is derived by solving a modified Hamilton-Jacobi-Bellman equation. The conventional persistence of excitation condition is relaxed by using experience replay technique. The proposed control scheme ensures that all states of the snake robot are uniformly ultimate bounded which is analyzed by using the Lyapunov approach, and the tracking error asymptotically converges to a residual set. Simulation results are presented to verify the effectiveness of the proposed method.

Trajectory tracking of wheeled mobile robot by adopting iterative learning control with predictive, current, and past learning items

In this paper, an iterative learning control algorithm is adopted to solve the high-precision trajectory tracking issue of a wheeled mobile robot with time-varying, nonlinear, and strong-coupling dynamics properties. The designed iterative learning control law adopts predictive, current and past learning items to drive the state variables, and input variables, and outputs variables converge to the bounded scope of their desired values. The algorithm can enhance the control performance, stability and robust characteristics. The rigorous mathematical proof of the convergence character of the proposed iterative learning control algorithm is given. The feasibility, effectiveness, and robustness of the proposed algorithm are illustrated by quantitative experiments and comparative analysis. The experimental results show that the proposed iterative learning control algorithm has an outstanding control effect on the trajectory tracking issue of wheeled mobile robots.

A simple and novel helical drive in-pipe robot

Pipeline grids of various size and material are pervasive in today's modern society. The frequent inspection and maintenance of such pipeline grids have presented a tremendous challenge. It is advocated that only advanced robot design embedded with intelligent electronics and control algorithms could perform the job. Given the ever increasing demands for intelligent in-pipe robots, various in-pipe drive mechanisms have been reported. One of the simplest is helical wheel drives that have only one degree of freedom. All previously reported in-pipe helical drives are based on independent passive wheels that are tilted an angle. One of the major problems of current helical wheel drives is their unstable traction force. In this paper, instead of allowing the wheels to rotate independently, they are synchronized by adding a timing belt. This small change will result in significant improvement which will be highlighted in this paper. In the proposed driving method, tracking force is analyzed together with a comprehensive set of traction force measurement experiments. Both analysis and experiments have shown that the proposed mechanism has great potential for in-pipe robot drive design.