This paper presents a novel motion planning framework for mobile robots operating in dynamic and uncertain environments, with an emphasis on accurate trajectory prediction and safe, efficient obstacle avoidance. The proposed approach integrates search-based planning with deep learning techniques to improve both robustness and interpretability. A multi-sensor perception module is designed to classify obstacles as either static or dynamic, thereby enhancing environmental awareness and planning reliability. To address the challenge of motion prediction, we introduce the K-GRU Kalman method, which first applies K-means clustering to distinguish between high-speed and low-speed dynamic obstacles, then models their trajectories using a combination of Kalman filtering and gated recurrent units (GRUs). Compared to state-of-the-art RNN and LSTM-based predictors, the proposed method achieves superior accuracy and generalization. Extensive experiments in both simulated and real-world scenarios of varying complexity demonstrate the effectiveness of the framework. The results show an average planning success rate exceeding 60%, along with notable improvements in path safety and smoothness, validating the contribution of each module within the system.

Representing art using a robotic system is part of artificial intelligence in our lives, especially in the realm of emotional expression. Developing a painting robot involves addressing how to enable the robot to emulate human artistic processes, which often include imprecise techniques or errors akin to those made by human artists. This paper discusses our development of an innovative painting robot utilizing the sim-to-real approach within learning technology. Specifically, this pipeline operates under a deep reinforcement learning (DRL) framework designed to learn drawing strategies from training data derived from real-world settings, aiming for the robot’s proficiency in emulating human artistic expressions. Accordingly, the framework comprises two modules when given a target drawing image: the first module trains in a simulated environment to break down the target image into individual strokes; the second module then learns how to execute these strokes in a real environment. Our experiments have shown that this system can meet our objectives effectively.