# StarNet: Joint Action-Space Prediction with Star Graphs and Implicit Global Frame Self-Attention

arXiv: https://arxiv.org/abs/2111.13566 · HTML: https://mlsanity.com/paper/2111.13566/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2021.

## Built on by (most cited first, 12 of 12)

- [GoRela: Go Relative for Viewpoint-Invariant Motion Forecasting](https://mlsanity.com/paper/2211.02545/) (2022)
- [The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review](https://mlsanity.com/paper/2308.05731/) (2023)
- [A Diffusion-Model of Joint Interactive Navigation](https://mlsanity.com/paper/2309.12508/) (2023)
- [Bridging the Gap Between Multi-Step and One-Shot Trajectory Prediction via Self-Supervision](https://mlsanity.com/paper/2306.03367/) (2023)
- [Conditional Unscented Autoencoders for Trajectory Prediction](https://mlsanity.com/paper/2310.19944/) (2023)
- [DiPA: Probabilistic Multi-Modal Interactive Prediction for Autonomous Driving](https://mlsanity.com/paper/2210.06106/) (2022)
- [Geometric Deep Learning for Autonomous Driving: Unlocking the Power of Graph Neural Networks With CommonRoad-Geometric](https://mlsanity.com/paper/2302.01259/) (2023)
- [Pioneering SE(2)-Equivariant Trajectory Planning for Automated Driving](https://mlsanity.com/paper/2403.11304/) (2024)
- [Hybrid Machine Learning Model with a Constrained Action Space for Trajectory Prediction](https://mlsanity.com/paper/2501.03666/) (2025)
- [Deep Occupancy-Predictive Representations for Autonomous Driving](https://mlsanity.com/paper/2303.04218/) (2023)
- [Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient](https://mlsanity.com/paper/2405.13152/) (2024)
- [Driving is a Game: Combining Planning and Prediction with Bayesian Iterative Best Response](https://mlsanity.com/paper/2512.03936/) (2025)

## Abstract (arXiv)

In this work, we present a novel multi-modal multi-agent trajectory prediction architecture, focusing on map and interaction modeling using graph representation. For the purposes of map modeling, we capture rich topological structure into vector-based star graphs, which enable an agent to directly attend to relevant regions along polylines that are used to represent the map. We denote this architecture StarNet, and integrate it in a single-agent prediction setting. As the main result, we extend this architecture to joint scene-level prediction, which produces multiple agents' predictions simultaneously. The key idea in joint-StarNet is integrating the awareness of one agent in its own reference frame with how it is perceived from the points of view of other agents. We achieve this via masked self-attention. Both proposed architectures are built on top of the action-space prediction framework introduced in our previous work, which ensures kinematically feasible trajectory predictions. We evaluate the methods on the interaction-rich inD and INTERACTION datasets, with both StarNet and joint-StarNet achieving improvements over state of the art.