DeepMoTIon: Learning to Navigate Like Humans

TL;DR

DeepMoTIon is a novel robot navigation method that learns from human pedestrian data to navigate safely and efficiently in crowds, outperforming benchmarks in imitation accuracy and success rate.

Contribution

It introduces a deep learning model trained on pedestrian data to enable robots to navigate like humans while respecting social norms.

Findings

Achieved 24% reduction in path deviation compared to benchmarks.

Reached the target in 100% of test cases, ensuring safety and social norm compliance.

Outperformed all benchmarks in human imitation accuracy.

Abstract

We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to navigate to the target location. We conduct extensive experiments to assess the components of our network and prove their necessity to imitate humans. Our experiments show that DeepMoTIion outperforms all the benchmarks in terms of human imitation, achieving a 24% reduction in time series-based path deviation over the next best approach. In addition, while many other approaches often failed to reach the target, our method reached the target in 100% of the test cases while complying with social norms and ensuring human safety.