Physics-Guided Multi-Modal Motion Prediction with Interaction-Aware GRU
TL;DR
A compact decoder in which each of the six futures is represented as a CTRA anchor plus an autoregressive position residual, which generates a useful six-mode set, but still needs better probability ranking for top-1 selection.
Abstract
In the Argoverse 2 experiments reported here, the simplest Constant Turn Rate and Acceleration (CTRA) decoder was stable but missed many interaction-driven turns and merges, while residual decoders without enough control improved early displacement but increased final-horizon error. This paper therefore studies a compact decoder in which each of the six futures is represented as a CTRA anchor plus an autoregressive position residual. The residual gated recurrent unit (GRU) is initialized from fused target-history, top-k neighbor, and lane-polyline context, and its contribution is scaled by a mode-specific gate and learned exponential decay. On the 10k/2k sanity ablations, CTRA-only decoding reached minFDE6=7.189 m, while autoregressive residuals with a larger correction GRU reduced it to 4.157 m; removing the gate increased it again to 4.946 m. On the full Argoverse 2 validation split, the final configuration achieves a minimum average displacement error of minADE6=1.21 m and a minimum final displacement error of minFDE6=2.78 m. The reported diagnostics show that the compact model generates a useful six-mode set, but still needs better probability ranking for top-1 selection.