Research on Industrial Robot Path Planning Optimization Algorithm Based on IoT and Deep Reinforcement Learning

With the rapid development of Industry 4.0, industrial robots are increasingly widely used in intelligent manufacturing. Path planning is one of its core tasks, directly affecting production efficiency and safety. Traditional path planning methods are often complex to consider in real-time and optimally when facing a complex dynamic environment. For this purpose, the present study introduces an optimization algorithm for industrial robot path planning, using the Internet of Things (IoT) and deep reinforcement learning (DRL) technologies. The algorithm collects environmental data in real-time through IoT technology and combines deep reinforcement learning models to make dynamic decisions to achieve efficient and adaptive path planning. The simulation outcomes show that in the simulated industrial environment, compared with the conventional A* algorithm and ant colony algorithm, this algorithm has an average 35% reduction in path planning time, a 22% improvement in path length optimization, and a success rate over 95% for obstacle avoidance in dynamic obstacle situations. The algorithm can rapidly adapt to environmental changes via real-time data feedback from IoT devices, and the volatility of the planning time is reduced by 40%. This research offers a novel approach for industrial robot path planning in intricate settings, with significant practical worth and potential for widespread adoption.