Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023
This work addresses the challenge of realistic agent simulation for autonomous driving systems, representing an incremental improvement with specific gains in a domain-specific competition.
The paper tackles the problem of closed-loop simulation of agents for autonomous driving by proposing the MultiVerse Transformer for Agent simulation (MVTA), which achieves a realism meta-metric of 0.5091 and an enhanced version MVTE reaches 0.5168, outperforming all other methods in the Waymo Open Sim Agents Challenge 2023.
This technical report presents our 1st place solution for the Waymo Open Sim Agents Challenge (WOSAC) 2023. Our proposed MultiVerse Transformer for Agent simulation (MVTA) effectively leverages transformer-based motion prediction approaches, and is tailored for closed-loop simulation of agents. In order to produce simulations with a high degree of realism, we design novel training and sampling methods, and implement a receding horizon prediction mechanism. In addition, we introduce a variable-length history aggregation method to mitigate the compounding error that can arise during closed-loop autoregressive execution. On the WOSAC, our MVTA and its enhanced version MVTE reach a realism meta-metric of 0.5091 and 0.5168, respectively, outperforming all the other methods on the leaderboard.