Deep-Learning Based Trajectory Forecast for Safety of Intersections with Multimodal Traffic (Phase II)

Details

• Creators:
  Mohamed, Abduallah ; Qian, Kun ; Claudel, Christian
• Corporate Creators:
  University of North Carolina at Charlotte. Center for Advanced Multimodal Mobility Solutions and Education
• Corporate Contributors:
  United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; United States. Department of Transportation. University Transportation Centers (UTC) Program
• Subject/TRT Terms:
  • Algorithms
  • Forecasting
  • Intersections
  • Machine learning
  • Neural networks
  • Pedestrians
  • Traffic safety
  • Trajectory
  • Validation
• Publication/ Report Number:
  2019 Project 08;CAMMSE-UNCC-2019-UTC-Project-08
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  University of North Carolina at Charlotte. Center for Advanced Multimodal Mobility Solutions and Education
• Abstract:
  Predicting pedestrian trajectories is of major importance for several applications including autonomous driving and surveillance systems. In autonomous driving, an accurate prediction of pedestrians trajectories enables the controller to plan ahead the motion of the vehicle in an adversarial environment. For example, it is a critical component for collision avoidance systems or emergency braking systems. In general traffic collision avoidance systems, such component would be very important in the synthesis of controller actions, preventing a collision. The objective of this report is to introduce a novel computational method for solving the trajectory prediction problem, using a combination of artificial neural networks (convolutional neural networks) and graph theory.
• Format:
  PDF
• Funding:
  69A3551747133
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/57039/dot_57039_DS1.pdf
• File Type:
  [PDF - 1.13 MB]
• Collection(s):
  University Transportation Centers ; US Transportation Collection
• Main Document Checksum:
  urn:sha-512:c36c4047d0ecca7fdea1823b159cbeea5852c582405796f3b2824d225fc86e1b4650b57efde7de559a14b85c1dc12d34b8534828243a7dcf2af7e0062615cfcf