CASNSC: A context-based approach for accurate pedestrian motion prediction at intersections

Intention recognition of pedestrians is crucial to safe and reliable working of 1 autonomous vehicles, when serving as, for instance, indoor service robots or 2 self-driving cars in busy urban scenes. Previously, Chen et al. [2016] combined 3 Markovian-based and clustering-based approaches to learn motion primitives and 4 subsequently predict pedestrian trajectories by modeling the transition between 5 learned primitives as a Gaussian Process (GP). This work further develops their ap6 proach by incorporating semantic features from the environment (relative distance 7 to curbside and status of pedestrian traffic lights) for more confident prediction of 8 pedestrian trajectories at intersections. Adding the environmental context, when 9 available, not only makes prediction more robust but can also provide increased 10 flexibility of prediction in new environments. We test our algorithm on real data. 11 The results show 26% improvement in prediction accuracy as compared to previous 12 work, on incorporation of new features. 13