Multi-Modal Model Predictive Control through Batch Non-Holonomic Trajectory Optimization: Application to Highway Driving

TL;DR

This paper introduces a real-time multi-modal MPC for highway driving that uses batch non-holonomic trajectory optimization, enabling efficient global search over multiple driving strategies and outperforming existing methods in speed and decision-making.

Contribution

It presents a novel batch non-holonomic trajectory optimization method that is parallelizable and suitable for real-time multi-modal MPC in highway driving scenarios.

Findings

Achieves up to 6x faster trajectory computation than baselines.

Automatically makes lane-change and overtaking decisions.

Effectively captures multi-modal driving behaviors in real traffic scenarios.

Abstract

Standard Model Predictive Control (MPC) or trajectory optimization approaches perform only a local search to solve a complex non-convex optimization problem. As a result, they cannot capture the multi-modal characteristic of human driving. A global optimizer can be a potential solution but is computationally intractable in a real-time setting. In this paper, we present a real-time MPC capable of searching over different driving modalities. Our basic idea is simple: we run several goal-directed parallel trajectory optimizations and score the resulting trajectories based on user-defined meta cost functions. This allows us to perform a global search over several locally optimal motion plans. Although conceptually straightforward, realizing this idea in real-time with existing optimizers is highly challenging from technical and computational standpoints. With this motivation, we present a novel batch non-holonomic trajectory optimization whose underlying matrix algebra is easily parallelizable across problem instances and reduces to computing large batch matrix-vector products. This structure, in turn, is achieved by deriving a linearization-free multi-convex reformulation of the non-holonomic kinematics and collision avoidance constraints. We extensively validate our approach using both synthetic and real data sets (NGSIM) of traffic scenarios. We highlight how our algorithm automatically takes lane-change and overtaking decisions based on the defined meta cost function. Our batch optimizer achieves trajectories with lower meta cost, up to 6x faster than competing baselines.