An autonomous robot vehicle with dynamic path planning

Abstract

An autonomous robotic vehicle with dynamic path planning capabilities, including: a dynamic path planning module configured to generate and adapt navigation paths in real time based on environmental changes and mission objectives; a sensor fusion module that integrates data from multiple sensors, including LiDAR, radar, cameras, ultrasonic sensors and GPS, to create a comprehensive environmental model; an obstacle avoidance module capable of detecting and predicting both stationary and moving obstacles and modifying the navigation path to avoid collisions; an artificial intelligence-based decision-making module for analyzing environmental data and learning from past navigation scenarios for improved performance; a decentralized control module that enables the independent operation of the vehicle in areas with interrupted or no connection to a central server; an energy management module configured to optimize battery usage by dynamically adjusting operating parameters based on real-time data and mission requirements; a cooperation module that enables communication and coordination between multiple autonomous robot vehicles for fleet management or the synchronized execution of tasks; a fail-safe module to ensure uninterrupted operation and data security in the event of communication failures or hardware malfunctions.

Description

[0001] The present invention relates to autonomous robotic vehicles and, more particularly, to a system and method for dynamic path planning and obstacle avoidance in real time using advanced sensing, computational algorithms and machine learning techniques.

[0002] Autonomous robotic vehicles (ARVs) have proven to be indispensable tools in various industries such as logistics, agriculture, and urban transportation, offering significant benefits by enabling unmanned operations, reducing costs, and increasing productivity. Despite their potential, conventional ARV systems face critical limitations that hamper their effectiveness in dynamic and complex environments. These systems typically rely on static trajectory planning algorithms such as Dijkstra or A*, which are well-suited for predictable and controlled scenarios but lack the flexibility to adapt to sudden changes in the environment, such as moving obstacles or unforeseen detours.

[0003] The sensing capabilities of conventional ARVs are often limited to a limited range of technologies, including GPS, ultrasonic sensors, or cameras, which perform adequately under ideal conditions but become unreliable in environments with poor visibility, occlusion, or weak GPS signals. For example, ARVs deployed indoors, underground, or in densely populated urban areas can lose their GPS functionality, leading to navigation errors. Likewise, cameras can fail in low-light or strong glare conditions, while ultrasonic sensors have limited range and resolution, making them unsuitable for detecting complex obstacles.

[0004] Another significant disadvantage of conventional systems is their reliance on reactive obstacle avoidance mechanisms. These systems detect obstacles only when encountered and make ad hoc adjustments to avoid collisions, often without considering the broader mission context or exploring alternative routes. This reactive approach leads to inefficient navigation, increased energy consumption, and longer operating times, especially in environments with frequent or unexpected changes.

[0005] Furthermore, conventional ARVs lack advanced decision-making and learning capabilities. They are unable to predict or proactively respond to dynamic obstacles, such as moving vehicles or pedestrians, and cannot learn from past experiences to improve their future performance. This lack of adaptability significantly reduces their operational efficiency and safety in dynamic, real-world scenarios.

[0006] Another limitation of conventional ARVs is their dependence on centralized control systems. Centralized control requires constant communication between the ARV and a central processing unit, making these systems vulnerable to communication failures, latency, or complete operational outages in areas with poor or intermittent connectivity. This dependence limits their scalability and operational autonomy, especially in large-scale or remote deployments.

[0007] Finally, the computational demands of processing complex environments can overwhelm conventional ARVs. While some systems attempt to address these challenges by incorporating high-resolution sensors, the resulting data requires significant processing power, slowing response times, increasing energy consumption, and limiting the vehicle's operating time.

[0008] To solve the problem, the present invention provides an autonomous robot vehicle system with dynamic path planning capabilities.

[0009] The autonomous robot vehicle system with dynamic path planning capabilities, capable of real-time path planning and replanning to adapt to sudden changes in the environment, including moving obstacles, unexpected roadblocks, or dynamic traffic conditions.

[0010] The autonomous robotic vehicle system with dynamic path planning capabilities integrated with advanced sensors such as LiDAR, radar, ultrasonic sensors, GPS and cameras along with sensor fusion algorithms to ensure accurate perception and navigation in various environments, including areas with poor visibility, occlusions or weak GPS signals.

[0011] The autonomous robot vehicle system with dynamic path planning capabilities that enable proactive and efficient obstacle avoidance by predicting and reacting to dynamic objects, ensuring safe and smooth navigation without unnecessary detours or delays.

[0012] The autonomous robotic vehicle system with dynamic path planning capabilities incorporating artificial intelligence (AI) and machine learning (ML) algorithms for advanced decision-making capabilities that enable the ARV to learn from past experiences and improve performance over time.

[0013] The autonomous robotic vehicle system with dynamic path planning capabilities, designing a decentralized control architecture that allows the ARV to operate independently without relying on continuous communication with a central server, ensuring uninterrupted operation in areas with limited or intermittent connectivity.

[0014] The autonomous robotic vehicle system with dynamic path planning capabilities that support coordination between multiple ARVs enables collaborative operations in tasks such as fleet management, swarm robotics, and synchronized logistics.

[0015] The autonomous robotic vehicle system with dynamic path planning capabilities that optimize energy consumption through the use of efficient algorithms and hardware, ensuring longer operating life and cost efficiency.

[0016] The autonomous robot vehicle system with dynamic path planning capabilities is capable of operating in a variety of environments, including indoor, outdoor, urban and rural, making it suitable for industries such as logistics, agriculture, construction and transportation.

[0017] The autonomous robotic vehicle system with dynamic trajectory planning capabilities that enhance the safety and reliability of the ARV by implementing fail-safe mechanisms, redundant systems, and predictive maintenance capabilities to minimize risks and ensure uninterrupted operation.

[0018] In one embodiment, an autonomous robotic vehicle with dynamic path planning capabilities is provided. The autonomous robotic vehicle (ARV) system with dynamic path planning capabilities addresses the limitations of conventional systems in dynamic and complex environments. The proposed system integrates advanced technologies, including real-time path planning algorithms, sensor fusion, and artificial intelligence, to enable seamless navigation in unpredictable environments. It features robust obstacle avoidance mechanisms that proactively predict and react to moving and stationary objects to ensure safe and efficient operation. A decentralized control architecture increases reliability by eliminating the dependence on constant communication with a central server, thus enabling uninterrupted performance even in areas with poor connectivity.The system is designed for scalability and supports collaboration between multiple ARVs for fleet management and synchronized tasks. Energy-efficient components and algorithms optimize operating time, while fail-safe mechanisms ensure safety and reliability. The versatile and cost-effective ARV system is suitable for various industries, including logistics, agriculture, and urban transport, and offers improved adaptability, efficiency, and user-friendliness.

[0019] The invention is explained again below with reference to the figure. It shows: Fig. : shows an autonomous robot vehicle with dynamic path planning.

[0020] Fig.shows an autonomous robotic vehicle with dynamic path planning capabilities. The autonomous robotic vehicle with dynamic trajectory planning capabilities includes a dynamic trajectory planning module, a sensor fusion module, an obstacle avoidance module, an artificial intelligence-based decision-making module, a decentralized control module, a collaborative module, and a fail-safe module. The dynamic path planning module is configured to generate and adapt navigation paths in real time based on environmental changes and mission objectives. The sensor fusion module integrates data from multiple sensors, including LiDAR, radar, cameras, ultrasonic sensors, and GPS, to create a comprehensive environmental model. The obstacle avoidance module detects and predicts stationary and moving obstacles and modifies the navigation path to avoid collisions.The artificial intelligence-based decision-making module analyzes environmental data and learns from past navigation scenarios to improve performance. The decentralized control module enables independent vehicle operation in areas with intermittent or no connection to a central server. The energy management module is configured to optimize battery usage by dynamically adjusting operating parameters based on real-time data and mission requirements. The collaborative module enables communication and coordination between multiple autonomous robot vehicles for fleet management or synchronized task execution. The fail-safe module ensures uninterrupted operation and data security in the event of communication failures or hardware malfunctions.The dynamic path planning module utilizes advanced algorithms, including reinforcement learning or hybrid optimization techniques, to improve adaptability and efficiency in complex environments. The sensor fusion module applies machine learning algorithms to combine data from multiple sensors, improving the accuracy of environmental feature detection under challenging conditions such as poor visibility or weak GPS signals. The obstacle avoidance module predicts the trajectory of moving obstacles and recalculates optimal navigation paths to ensure safety and operational efficiency.The artificial intelligence-based decision-making module is configured to prioritize mission objectives over predefined routes, optimize energy consumption based on environmental data, and continuously update navigation strategies by learning from historical operating data. The collaborative module supports the coordination of multiple autonomous robot vehicles in a fleet, enabling synchronized navigation and task execution. The decentralized control module includes fail-safe modules that ensure uninterrupted operation and data security in the event of communication failures or hardware failures. The energy management module adjusts operating parameters in real time to meet mission requirements, including energy consumption, battery status, and optimal path selection.The navigation path generated by the dynamic path planning module is updated in response to unexpected obstacles, changing terrain conditions, and changes in mission objectives or operational priorities. List of reference symbols 100 systems

Claims

[1] An autonomous robot vehicle with dynamic path planning capabilities, comprising: a dynamic path planning module configured to generate and adapt navigation paths in real time based on environmental changes and mission objectives; a sensor fusion module that integrates data from multiple sensors, including LiDAR, radar, cameras, ultrasonic sensors, and GPS, to create a comprehensive environmental model; an obstacle avoidance module capable of detecting and predicting both stationary and moving obstacles and modifying the navigation path to avoid collisions; an artificial intelligence-based decision-making module to analyze environmental data and learn from past navigation scenarios for improved performance; a decentralized control module that enables independent operation of the vehicle in areas with interrupted or no connection to a central server; an energy management module configured to optimize battery usage by dynamically adjusting operating parameters based on real-time data and mission requirements; a cooperation module that enables communication and coordination between multiple autonomous robot vehicles for fleet management or synchronized task execution; a fail-safe module to ensure uninterrupted operation and data security in the event of communication failures or hardware malfunctions. [2] The system of claim 1, wherein the dynamic path planning module uses advanced algorithms, including reinforcement learning or hybrid optimization techniques, to improve adaptability and efficiency in complex environments. [3] The system of claim 1, wherein the sensor fusion module applies machine learning algorithms to combine data from multiple sensors, thereby improving the accuracy of detecting environmental features under challenging conditions such as poor visibility or weak GPS signals. [4] The system of claim 1, wherein the obstacle avoidance module predicts the trajectory of moving obstacles and recalculates optimal navigation paths to maintain safety and operational efficiency. [5] The system of claim 1, wherein the artificial intelligence-based decision-making module is configured to prioritize mission objectives over predefined routes, optimize energy consumption based on environmental data, and continuously update navigation strategies by learning from historical operational data. [6] The system of claim 1, wherein the collaborative module supports the coordination of multiple autonomous robot vehicles in a fleet and enables synchronized navigation and task execution. [7] The system of claim 1, wherein the decentralized control module includes fail-safe modules to ensure uninterrupted operation and data security in the event of communication failures or hardware malfunctions. [8] The system of claim 1, wherein the power management module adjusts operating parameters in real time based on mission requirements, including power consumption, battery status, and optimal path selection. [9] The system of claim 1, wherein the navigation path generated by the dynamic path planning module is updated in response to unexpected obstacles, changes in terrain conditions, and modifications in mission objectives or operational priorities.

Images