Learning models of dynamical systems with external inputs, which may be, for example, nonsmooth or piecewise, is crucial for studying complex phenomena and predicting future state evolution, which is essential for applications such as safety guarantees and decision-making. In this work, we introduceInput Concomitant Neural ODEs (ICODEs), which incorporate precise real-time input information into the learning process of the models, rather than treating the inputs as hidden parameters to be learned. The sufficient conditions to ensure the model’s contraction property are provided to guarantee that system trajectories of the trained model converge to a fixed point, regardless of initial conditions across different training processes. We validate our method through experiments on several representative real dynamics: Single-link robot, DC-to-DC converter, motion dynamics of a rigid body, Rabinovich-Fabrikant equation, Glycolytic-glycogenolytic pathway model, and heat conduction equation. The experimental results demonstrate that our proposed ICODEs efficiently learn the ground truth systems, achieving superior prediction performance under both typical and atypical inputs. This work offers a valuable class of neural ODE models for understanding physical systems with explicit external input information, with potentially promising applications in fields such as physics and robotics. Our code is available online at https://github.com/EEE-ai59/ICODE.git.

Crawler robots are popular in tasks of urban search and rescue. Because of using tracks most of these robots have good traversability on rough terrains. For creating and testing these abilities and crawler robot itself often used simulators, which could help to reconstruct most of the conditions and environment without any difficulties. And this is a reason why most of the robots must have its simulation model.In this paper, we present a fully equipped and moving model of tracked robot Servosila "Engineer". It contains all of the sensors that used a real robot with the ability to get information from them via ROS topics through all the time of the simulation. Also, it has similar to real robot control elements, physic characteristics and useful crawler simulation.

This position paper deals with formalization of a practical scenario of using multiple aerial robots for monitoring an expanding area, which is a part of an operational framework and a global information system for real-time management of flood disasters caused by torrential rains. Two typical tasks of the optimal information coverage problem, represented by caging the disaster area and tracking its dynamic expansion are sketched. Three basic component of the minimal configuration of the control system-the image segmentation, Kalman filtering based tracking, and distributed formation control-are identified and reviewed.

This paper deals with motion planning and control problems for a class of partially differentially flat systems. A Betafunction based motion planning algorithm is first constructed by selecting the base variable to be the 2-nd order derivative of Beta-function weighted by a constant parameter. The proposed algorithm has lower computational cost than the optimal control while it provides similar system performance. Then, a function approximation technique based control algorithm is proposed by restructuring a partially differentially flat system in the form of the combination of an auxiliary linear system and its variation from the original system. The variation term was replaced by its approximation as a chosen basis function weighted by constant parameters to be determined. These unknown plant parameters are estimated at each instant, denoted by the adjustable control parameters using a defined update law.

An adaptive trajectory tracking problem for a spherical rolling robot driven by a 2DOF pendulum is considered in this paper. A feedback controller is proposed for the goal of tracking the trajectory for the full configuration of the spherical robot. To deal with time-varying uncertainty of the system dynamics, an adaptation mechanism is included in the trajectory tracking controller by parameterizing the system uncertainty with a polynomial function, weighted by unknown constant parameters adjustable by the defined update law. The constructed controller is first tested for the planar hoop-pendulum and then applied to the ball-pendulum system. The convergence to the desired trajectories under the control law is proved and then verified by simulations for tracking circular motions under perturbation.

This paper deals with motion planning and control for an underactuated system, the hoop-pendulum, a pendulum mounted at the center of a hoop. The dynamic model for this system is derived and the local controllability around the equilibrium point is established. To transfer the system from a initial configuration to a desired final configuration in rest-to-rest mode, two controllers, the feedback and feedforward ones, are constructed. The feedback controller stabilizes the system at the origin and is based on the construction of a suitable Lyapunov function. The feedforward controller is based on the representation of the motion of the pendulum by the second derivative of Beta function. The feasibility and the performance of the proposed controllers are verified under simulations.

This paper deals with a trajectory tracking problem for the ball-pendulum system, a spherical rolling robot driven by a two degree of freedom pendulum. The backstepping technique is applied and first tested on the hoop-pendulum system, a planar case of the ball-pendulum. By mimicking the backstepping process of the planar case, a feedback controller for the ball-pendulum system is then proposed, tracking motion trajectories for both the position and orientation of the spherical shell of the rolling robot. The validity of the constructed tracking controller is demonstrated by establishing the asymptotic stability of the error dynamics for the closed-loop system. The performance of the controller is verified under simulations for tracking linear and circular motions.

This paper deals with the dynamics and motion planning for a spherical rolling robot with a pendulum actuated by two motors. First a dynamic model for the rolling robot is established. In general, not all feasible kinematic trajectories of the rolling carrier are dynamically realizable. A notable exception is when the contact trajectories on the sphere and on the plane are geodesic lines. Based on this consideration, a motion planning strategy for complete reconfiguration of the rolling robot is proposed. The strategy consists of two trivial movements and a non-trivial maneuver that is based on tracing multiple spherical triangles. To compute the sizes and the number of triangles, a reachability diagram is constructed. To define the control torques realizing the rest-to-rest motion along the geodesic lines, two possible approaches are suggested. A computational algorithm, implementing the motion planning strategy, is developed and verified under simulation.

This paper deals with motion planning problems for spherical rolling robots driven by a two degree of freedom pendulum. A full dynamic model for this system is first introduced. Then, assuming that the contact path is specified and the sphere moves in pure rolling mode, the full dynamic model is reduced by imposing virtual constraints. A timing control law, based on the Beta function, for tracing the contact curves in rest-to-rest motion is constructed. The constructed control law is verified under simulation for tracing Viviani's curve and the Loxodrome on the sphere.