Robotic Fish Self-Learning Control for Fast Speed Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control methods for robotic fish struggle with achieving precise motion control in unstructured environments, requiring a systematic mathematical model and resulting in slow convergence of tracking errors, which is inadequate for applications like underwater tasks that demand consistent speed trajectories.
Innovation Solution
A high-order iterative self-learning control method is introduced, which constructs a control gain set, performs preferential iteration to optimize control gains, and uses high-order iterative calculations to continuously adjust the control input thrust, allowing the robotic fish to achieve rapid convergence and complete tracking of expected speed trajectories without relying on a precise mathematical model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional control methods (PID, fuzzy logic, sliding mode) are used, then the robotic fish can achieve asymptotic error convergence, but the tracking error convergence speed is slow
Solution Approach 1:
The patent performs preliminary actions by conducting multiple iterations to optimize control gain elements before final control execution. The iterative process pre-adjusts control parameters based on historical tracking errors, enabling faster convergence speed while maintaining reliability through cumulative learning from previous iterations.
Solution Approach 2:
The patent implements feedback mechanisms by using tracking errors from previous iterations to adjust control gains in subsequent iterations. The control gain elements are updated based on feedback from actual system performance, allowing the system to learn and improve convergence speed while maintaining stable error convergence through continuous feedback adjustment.
2Adaptability or versatility
If conventional control methods are used, then systematic and precise mathematical models are required, but this increases system complexity and reduces adaptability
Solution Approach 1:
The patent applies self-service by enabling the robotic fish control system to automatically optimize its own control parameters through iterative learning. The system serves itself by using its own tracking error data to adjust control gains, eliminating the need for external mathematical modeling while improving adaptability to unstructured environments through self-learning.
Solution Approach 2:
The patent implements parameter changes by dynamically adjusting control gain elements through iterative optimization. Instead of relying on fixed mathematical models, the system changes control parameters based on actual performance feedback, thereby reducing model complexity requirements while enhancing adaptability to varying environmental conditions.
3Ease of operation
If open-loop gait generation methods are used, then fish-like swimming motion can be generated, but the robotic fish cannot achieve expected motion in unstructured environments
Solution Approach 1:
The patent closes the control loop by implementing feedback mechanisms that use tracking errors to adjust control inputs. The iterative process continuously monitors actual motion performance and feeds this information back to refine control parameters, transforming open-loop gait generation into a closed-loop system that achieves both ease of operation and reliable motion control accuracy.
Solution Approach 2:
The patent performs preliminary adjustments to control parameters through iterative optimization before final control execution. By pre-tuning control gains based on historical performance data, the system maintains simple gait generation while improving motion control accuracy through preliminary parameter optimization.
Data Source
AI summary
The invention relates to a field off artificial intelligence (AI) technologies, and discloses a method and an apparatus for high-order iterative self-learning control for a robotic fish, and a storage medium; the control method performs preferential iterative calculation on control gain elements in the control gain set to obtain a target control gain set; and performs high-order iterative calculation according to the target control gains, the first control input thrust and the first tracking error to obtain a target control input thrust, and then controls a robotic fish to swing according to the target control input thrust to obtain an expected speed. In this way, complete tracking and rapid convergence of a swim speed of a robotic fish in the whole operation space may be achieved.