Fig 7 - uploaded by He Wang
Content may be subject to copyright.
The collision rate and the number of collisions against the number of agents are shown in (a) and (b) respectively. Both of horizontal axes represent the number of agents from 50 to 200. The vertical axes in (a) and (b) represent the collision rate and the number of collisions respectively.

The collision rate and the number of collisions against the number of agents are shown in (a) and (b) respectively. Both of horizontal axes represent the number of agents from 50 to 200. The vertical axes in (a) and (b) represent the collision rate and the number of collisions respectively.

Source publication
Preprint
Full-text available
Trajectory prediction has been widely pursued in many fields, and many model-based and model-free methods have been explored. The former include rule-based, geometric or optimization-based models, and the latter are mainly comprised of deep learning approaches. In this paper, we propose a new method combining both methodologies based on a new Neura...

Contexts in source publication

Context 1
... its collision rate increases with the growth of the number of agents, our method is still the best compared with the baselines and our predictions are more plausible. In addition, we also plot the relation between the collision rate (and the number of collisions) and the agent number ranging from 50 to 200 in Figure 7. Y-net is worse than S-CSR and NSP. ...
Context 2
... its collision rate increases with the growth of the number of agents, our method is still the best compared with the baselines and our predictions are more plausible. In addition, we also plot the relation between the collision rate (and the number of collisions) and the agent number ranging from 50 to 200 in Figure 7. Y-net is worse than S-CSR and NSP. ...