KI-PMF: Knowledge Integrated Plausible Motion Forecasting

The accurate prediction of surrounding traffic actors' movements is vital for the large-scale safe deployment of autonomous vehicles.Existing motion forecasting methods primarily aim to minimize prediction error by optimizing a loss function, which can sometimes lead to physically infeasible predictions or states that violate external constraints.This paper proposes a method that integrates explicit knowledge priors, allowing a network to forecast future trajectories that comply with both the vehicle's kinematic constraints and the driving environment's geometry.This is achieved by introducing a non-parametric pruning layer, and learnable attention layers to incorporate the defined knowledge priors.The proposed method aims to satisfy reachability guarantees and thus prevent off-road predictions common to a neural network in the motion forecasting realm.By conditioning the network to adhere to physical laws, we can achieve accurate and safe predictions, which are crucial for maintaining the safety and efficiency of autonomous vehicles in real-world settings.