Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction
This addresses motion prediction for autonomous agents in urban settings, but it appears incremental as it builds on kernel-based methods for multi-modal modeling.
The paper tackles the problem of predicting multi-modal and probabilistic future trajectories for agents like humans and vehicles in urban environments by introducing Kernel Trajectory Maps (KTM), which project observed waypoints onto representative trajectories to output a mixture of continuous stochastic processes, achieving results that capture complex motion patterns without specifying concrete numbers.
Understanding the dynamics of an environment, such as the movement of humans and vehicles, is crucial for agents to achieve long-term autonomy in urban environments. This requires the development of methods to capture the multi-modal and probabilistic nature of motion patterns. We present Kernel Trajectory Maps (KTM) to capture the trajectories of movement in an environment. KTMs leverage the expressiveness of kernels from non-parametric modelling by projecting input trajectories onto a set of representative trajectories, to condition on a sequence of observed waypoint coordinates, and predict a multi-modal distribution over possible future trajectories. The output is a mixture of continuous stochastic processes, where each realisation is a continuous functional trajectory, which can be queried at arbitrarily fine time steps.