GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting

TL;DR

GoRela introduces a viewpoint-invariant motion forecasting method that efficiently encodes spatial relationships using relative positional encodings, improving scalability and generalization for autonomous vehicle prediction tasks.

Contribution

The paper presents a novel shared encoding approach with pair-wise relative positional encodings that are viewpoint-invariant, reducing computation and enhancing generalization in motion forecasting.

Findings

Achieves state-of-the-art accuracy on Argoverse 2 benchmark.

Demonstrates strong generalization on a new highway dataset.

Reduces online computation by reusing offline map embeddings.

Abstract

The task of motion forecasting is critical for self-driving vehicles (SDVs) to be able to plan a safe maneuver. Towards this goal, modern approaches reason about the map, the agents' past trajectories and their interactions in order to produce accurate forecasts. The predominant approach has been to encode the map and other agents in the reference frame of each target agent. However, this approach is computationally expensive for multi-agent prediction as inference needs to be run for each agent. To tackle the scaling challenge, the solution thus far has been to encode all agents and the map in a shared coordinate frame (e.g., the SDV frame). However, this is sample inefficient and vulnerable to domain shift (e.g., when the SDV visits uncommon states). In contrast, in this paper, we propose an efficient shared encoding for all agents and the map without sacrificing accuracy or generalization. Towards this goal, we leverage pair-wise relative positional encodings to represent geometric relationships between the agents and the map elements in a heterogeneous spatial graph. This parameterization allows us to be invariant to scene viewpoint, and save online computation by re-using map embeddings computed offline. Our decoder is also viewpoint agnostic, predicting agent goals on the lane graph to enable diverse and context-aware multimodal prediction. We demonstrate the effectiveness of our approach on the urban Argoverse 2 benchmark as well as a novel highway dataset.