ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting
This work addresses collision avoidance in trajectory forecasting for applications like autonomous driving and robotics, representing an incremental improvement by enhancing existing models with a new module.
The paper tackles the problem of human trajectory forecasting models overlooking environmental obstacles, which leads to collisions, by introducing ECAM, a contrastive learning-based module that reduces collision rates by 40-50% when integrated with state-of-the-art methods on the ETH/UCY dataset.
Human trajectory forecasting is crucial in applications such as autonomous driving, robotics and surveillance. Accurate forecasting requires models to consider various factors, including social interactions, multi-modal predictions, pedestrian intention and environmental context. While existing methods account for these factors, they often overlook the impact of the environment, which leads to collisions with obstacles. This paper introduces ECAM (Environmental Collision Avoidance Module), a contrastive learning-based module to enhance collision avoidance ability with the environment. The proposed module can be integrated into existing trajectory forecasting models, improving their ability to generate collision-free predictions. We evaluate our method on the ETH/UCY dataset and quantitatively and qualitatively demonstrate its collision avoidance capabilities. Our experiments show that state-of-the-art methods significantly reduce (-40/50%) the collision rate when integrated with the proposed module. The code is available at https://github.com/CVML-CFU/ECAM.