Explainable Action Prediction through Self-Supervision on Scene Graphs

Pawit Kochakarn, Daniele De Martini, Daniel Omeiza, Lars Kunze
2/7/2023
cs.CVcs.RO

No confident code implementation found for this paper.

Abstract

This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a self-supervision pipeline to infer representative and well-separated embeddings. Key aspects are interpretability and explainability; as such, we embed in our architecture attention mechanisms that can create spatial and temporal heatmaps on the scene graphs. We evaluate our system on the ROAD dataset against a fully-supervised approach, showing the superiority of our training regime.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Predicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving

86% match2025

Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention

85% match2024

Enhancing End-to-End Autonomous Driving with Latent World Model

85% match1 repo3932024

Towards Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations

84% match2024

A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes

84% match2026

PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network

84% match2024

Cite this paper

@article{kochakarn2023explainable,
  title  = {Explainable Action Prediction through Self-Supervision on Scene Graphs},
  author = {Pawit Kochakarn and Daniele De Martini and Daniel Omeiza and Lars Kunze},
  year   = {2023},
  eprint = {2302.03477},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.03477v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.03477.svg)](https://codeofpaper.com/paper/2302.03477)

Discussion