Description:[0001] This invention pertains to the field of robotic systems and artificial intelligence, specifically focusing on the optimization of path planning for autonomous robots. Path planning is a crucial aspect of robotic navigation, where the objective is to determine the most efficient route for a robot to reach its destination while avoiding obstacles and minimizing energy consumption. The invention leverages advanced artificial intelligence algorithms, including machine learning and reinforcement learning techniques, to enhance the decision-making process in real-time, enabling robots to navigate complex environments with higher efficiency and reliability. This field of invention is particularly relevant to industries such as manufacturing, logistics, healthcare, and service robotics, where autonomous robots are increasingly deployed for various tasks.
[0002] Additionally, the invention addresses the problem of vehicle scheduling within multi-robot systems, ensuring coordinated movement and task execution. By applying intelligent search strategies and AI-driven optimization methods, the invention aims to improve the overall performance and effectiveness of robotic fleets. This includes reducing the number of explorations needed to find optimal paths, speeding up the convergence process, and minimizing the overlap of travel routes among multiple robots. The advancements presented in this invention have the potential to significantly enhance the operational capabilities of autonomous robotic systems, leading to greater productivity and cost savings in various applications.

Background

[0003] Robotic path planning is a foundational element of autonomous navigation, enabling robots to move efficiently from one point to another within a given environment. Traditionally, path planning algorithms have relied on heuristic methods and rule-based systems to navigate. While these methods have been effective to some extent, they often fall short in dynamic and complex environments where unforeseen obstacles and variable conditions can significantly impact the robot's ability to find an optimal path. As the deployment of robots across various industries continues to grow, the need for more sophisticated and adaptive path planning solutions becomes increasingly apparent.
[0004] Artificial intelligence (AI) has emerged as a transformative technology in addressing the limitations of traditional path planning methods. AI algorithms, particularly those based on machine learning and reinforcement learning, offer the ability to learn from data and experience, adapting to new situations and improving over time. These capabilities are crucial for developing more robust and efficient path planning systems that can handle the complexities of real-world environments. By incorporating AI, robots can make informed decisions in real-time, optimizing their routes based on current conditions and historical data, which significantly enhances their operational efficiency and reliability.

[0005] One of the critical challenges in multi-robot systems is the coordination of multiple robots to achieve a common goal without interfering with each other. Vehicle scheduling, or the task of assigning and organizing the movement of robots, plays a vital role in this context. Effective vehicle scheduling ensures that robots can complete their tasks in a coordinated manner, minimizing delays and avoiding collisions. Traditional scheduling approaches often struggle with scalability and efficiency, especially as the number of robots increases. AI-driven optimization methods can address these challenges by providing more dynamic and scalable solutions for vehicle scheduling in multi-robot systems.
[0006] The application of AI in path planning and vehicle scheduling not only improves the individual performance of robots but also enhances the overall system efficiency. By reducing the number of explorations required to find optimal paths and accelerating the convergence process, AI algorithms can significantly lower the computational burden and operational costs. This is particularly important in industries such as manufacturing, logistics, and healthcare, where the timely and efficient operation of robotic systems is critical. The advancements in AI-driven path planning and vehicle scheduling are paving the way for more intelligent, adaptable, and efficient robotic systems, contributing to the broader goal of achieving greater automation and productivity in various sectors.
[0007] IN201841029392 This patent discloses a method and system for path planning for a robot using artificial intelligence techniques. The method involves generating multiple candidate paths for the robot, evaluating each candidate path based on predetermined criteria, and selecting a path based on the evaluation to navigate the robot. By employing AI algorithms, the system can dynamically adjust the robot's path in real-time, optimizing its trajectory based on environmental conditions and obstacles, thereby enhancing its efficiency and effectiveness in navigating complex environments.
[0008] IN201711023881 This patent presents a system and method for intelligent path planning for robotic navigation. The system utilizes machine learning algorithms to analyze real-time sensor data and generate optimal paths for the robot to navigate in dynamic environments. By integrating AI into the path planning process, the system can improve the robot's ability to avoid obstacles, navigate complex terrain, and optimize its trajectory, leading to enhanced efficiency and effectiveness in robotic navigation.
[0009] IN201711031641: This patent introduces an AI-enabled path planning system for robotic applications. The system utilizes deep learning algorithms for efficient paths for robots to navigate in complex and dynamic environments. By AI, the system can optimize path planning based on real-time data, improving to navigate challenging terrain and avoid obstacles, thereby enhancing its overall performance and efficiency.
Objects of the Invention

[0010] The objects of invention are as follows:
• AI algorithms predict optimal paths for robots based on real-time environmental data.
• Dynamic adjustments to paths are made in real-time to optimize efficiency in changing conditions
• Obstacle avoidance strategies are employed to ensure safe and efficient path planning.
• Focus on minimizing energy consumption through optimized path planning.
• Real-time adaptation of paths based on new information improves responsiveness.
• Learning from past experiences enhances future path planning decisions.
• Coordination of paths for multiple robots to avoid collisions and optimize operations.
• Ability to navigate through complex and cluttered environments
• Safety protocols prioritize the safety of the robot and its surroundings.
• User-friendly interface for easy monitoring and control of robotic path planning.

, Claims:[1] A method for optimizing robot path planning, comprising defining a set of actions for the robot to choose from when encountering a new state; implementing a search strategy during action selection to enhance algorithm performance; utilizing an artificial intelligence algorithm to select the optimal action that maximizes overall return; incorporating directional reference vehicle scheduling to guide the robot's movement; wherein the method improves path planning efficiency by reducing exploration and accelerating convergence.
[2] A system for optimizing vehicle scheduling in a multi-robot environment, comprising defining a path variable based on planning nodes and delivery requirements; identifying a sequence of delivery points that form a legitimate sub-path, excluding repeated planning points; employing an artificial intelligence algorithm to optimize the scheduling of vehicles; wherein the system increases efficiency by minimizing the number of explorations required and speeding up the convergence process.
[3] A directional reference vehicle scheduling method for robot path planning, comprising establishing planning nodes and delivery points that define the path variable; creating a sequence of delivery points meeting delivery requirements to form a legitimate sub-path; utilizing directional reference data to schedule vehicle movements efficiently; applying an artificial intelligence algorithm to select optimal actions based on the directional reference; wherein the method enhances the overall efficiency of the multi-robot system by reducing redundant explorations and improving convergence speed.
[4] A method for enhancing the efficiency of multi-robot path planning, comprising defining a set of actions and planning nodes for robot movement; employing a search strategy for action selection to maximize overall return; utilizing an artificial intelligence algorithm to identify optimal paths and actions; incorporating directional reference vehicle scheduling to guide robots accurately; wherein the method significantly boosts multi-robot system efficiency by decreasing the number of required explorations and expediting the convergence of the path planning algorithm.