Transferable Pedestrian Motion Prediction Models at Intersections

One desirable capability of autonomous cars is to accurately predict the pedestrian motion near intersections for safe and efficient trajectory planning. We are interested in developing transfer learning algorithms that can be trained on the pedestrian trajectories collected at one intersection and yet still provide accurate predictions of the trajectories at another, previously unseen intersection. We first discussed the feature selection for transferable pedestrian motion models in general. Following this discussion, we developed one transferable pedestrian motion prediction algorithm based on Inverse Reinforcement Learning (IRL) that infers pedestrian intentions and predicts future trajectories based on observed trajectory. We evaluated our algorithm at three intersections. We used the accuracy of augmented semi-nonnegative sparse coding (ASNSC), trained and tested at the same intersection as a baseline. The result shows that the proposed algorithm improves the baseline accuracy by a statistically significant percentage in both non-transfer task and transfer task.

Authors

• Macheng Shen
• Golnaz Habibi
• Jonathan P. How

Keywords

• Trajectory
• Hidden Markov models
• Semantics
• Predictive models
• Prediction algorithms
• Feature extraction
• Reinforcement learning
• Walking
• Prediction Model
• Motion Prediction
• Pedestrian Motion Prediction
• Prediction Accuracy
• Learning Algorithms
• Transfer Learning
• Motion Model
• Future Trajectories
• Transfer Task
• Inverse Reinforcement Learning
• Pedestrian Trajectory
• Model Parameters
• Flow Velocity
• Hidden Markov Model
• Parametrized
• Radial Function
• Gaussian Process
• Coordinate Transformation
• Discrete Distribution
• Markov Decision Process
• Semantic Context
• Reward Function
• Coordinate Frame
• Markov Decision Process Model
• Semantic Labels
• Heading Angle
• Training Trajectories
• Trajectory Prediction
• Low Reward