A5024710833- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Control and Dynamics of Mobile Robots
- Robotic Locomotion and Control
- Adaptive Control of Nonlinear Systems
- Iterative Learning Control Systems
- Mechanics and Biomechanics Studies
- EEG and Brain-Computer Interfaces
- Transportation and Mobility Innovations
- Mechanical Systems and Engineering
- Advanced Control Systems Optimization
- Advanced Theoretical and Applied Studies in Material Sciences and Geometry
- Engineering Technology and Methodologies
- Advanced Vision and Imaging
- Robotic Mechanisms and Dynamics
- Robot Manipulation and Learning
- Autonomous Vehicle Technology and Safety
- Robotics and Automated Systems
- Human Pose and Action Recognition
- Multimodal Machine Learning Applications
Moscow Institute of Physics and Technology
2019-2024
In this paper, the motion control of robotic rigid two-link manipulator using an adaptive LQ-based computed-torque controller is studied in presence unknown parameters dynamic model. This consists a linear quadratic one, and update rule for estimating parameters. The regulator (LQR) presents optimal solution to minimize tracking error. advantage mechanism that accuracy carrying loads will improve with time because adaptation continues getting feedback signal from
We address a task of local trajectory planning for the mobile robot in presence static and dynamic obstacles. Local is obtained as numerical solution Model Predictive Control (MPC) problem. Collision avoidance may be provided by adding repulsive potential obstacles to cost function MPC. develop an approach, where estimated neural model. propose explore three possible strategies handling First, environment with considered sequence environments. Second, model predict at once. Third, future...
A method of adaptive control a specialized manipulator designed to work as part robotic complex for servicing vertical surfaces is proposed and studied. The consists wheeled platform, movement robot with vacuum contact device manipulator. article describes the operation at stage bringing work. suggested controller contains computed torque eliminate nonlinearity in model, addition linear quadratic regulator achieve an optimal tracking error. Finally, mechanism added process uncertainties...
The task of local trajectory planning for an autonomous wheeled robotic platform in cluttered indoor environment is considered. Such might include narrow passages, which width less than the length platform. Therefore, it not possible to apply standard approach, when obstacles are inflated with maximum radius We propose a novel approach based on numerical solution nonlinear model predictive control task. Oblong shape approximated high-order ellipse. define differentiable sigmoid po-tential...
Model predictive control (MPC) may provide local motion planning for mobile robotic platforms. The challenging aspect is the analytic representation of collision cost case when both obstacle map and robot footprint are arbitrary. We propose a Neural Potential Field: neural network model that returns differentiable based on pose, map, footprint. differentiability our allows its usage within MPC solver. It computationally hard to solve problems with very high number parameters. Therefore,...
A robotic complex consisting of a transport-handling platform and climbing robot installed on it is considered. The designed to move the horizontal surface place vertical surface. practical implementation control algorithm described, which makes possible automate process placing