The role of robot following is crucial for effective human-robot collaboration. Traditional methods often rely on maintaining a significant distance between the robot and the human, which limits interaction and responsiveness. In contrast, close-proximity front-following facilitates immediate engagement, enhancing user experience and improving human-robot interaction. Nonetheless, it presents challenges in accurately interpreting human walking intentions due to a restricted observational field. In our paper, we introduce an innovative Depth-Temporal Attention Network that takes lower-limb depth images and robot motor signals as input, to accurately predict human walking intentions. This network leverages a depth attention module to capture essential spatial features and integrates a temporal attention mechanism to analyze movement dynamics. To enhance generalization, we use a domain adversarial module that focuses on shared features across diverse walking data, ensuring consistent performance across users. Experimental results demonstrate that our approach achieves an impressive average intention prediction accuracy of 91.09%, significantly surpassing baseline models by 12.59% to 23.66%. Additionally, an ablation study reveals that the depth-attention module substantially improves the model's understanding of depth features, resulting in an 11.44% increase in accuracy. With this high prediction accuracy, smooth front-following is achieved at close-proximity.

With the ever-increasing elderly population, elder walking assistance is in strong demand. Instead of receiving assistance from a human carer, a smart walker can bring an elder user a more convenient and autonomous walking experience. Towards intelligent and safe walking assistance, we propose a close-proximity front-following model for smart walkers, which analyzes the walking gait and detects the walking intention of the user, and intelligently follows the user in the front to provide walking support, without the user pushing the walker. We design a deep learning model named Front-Following Net (FFLNet), consisting of CNN and LSTM networks to extract spatial and temporal features of the elder walking gait, collected in time windows through a thermal camera and a 2D LiDAR, for effective walking intention detection. As compared to other walking intention detection approaches, our model can explore more effective information in the gait data within a short walking period, and achieve accurate hands-free tracking of the user. Experiments show that our FFLNet can achieve over 77% detection accuracy among six representative walking intentions and more than 90% accuracy for turning intentions. Combined with a carefully designed walker control policy, our smart walker can achieve high front-following correctness with the user.