Predicting Human Trajectories by Learning and Matching Patterns
arXiv:2104.10241
Abstract
As more and more robots are envisioned to cooperate with humans sharing the same space, it is desired for robots to be able to predict others' trajectories to navigate in a safe and self-explanatory way. We propose a Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC). A set of experiments carried out on the human trajectory prediction problem shows that our model performs comparably to the state of the art and outperforms in some cases. More importantly, the proposed approach unveils the obscurity in the previous use of a pooling layer, presenting a way to intuitively explain the decision-making process.
arXiv commentThesis document of the degree of Master of Science in Robotics of Carnegie Mellon University School of Computer Science
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Social Force Model for Pedestrian Dynamics
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark
- Following Social Groups: Socially Compliant Autonomous Navigation in Dense Crowds