G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System
This work addresses trajectory prediction for social robots to avoid human obstructions, but it is incremental as it builds on existing methods with architectural and data enhancements.
The paper tackles the problem of predicting out-of-domain human and agent trajectories for autonomous drone navigation, achieving a 9.5% improvement in Final Displacement Error (FDE) on the PECNet benchmark.
Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git