Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction

• URL: http://arxiv.org/abs/2312.02872v1
• Date: Tue, 5 Dec 2023 16:39:32 GMT
• Title: Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction
• Authors: Angie Nataly Melo, Carlota Salinas and Miguel Angel Sotelo
• Abstract summary: This research introduces a novel neuro-symbolic approach that combines deep learning and fuzzy logic for an explainable and interpretable pedestrian crossing prediction. We have developed an explainable predictor (ExPedCross), which utilizes a set of explainable features and employs a fuzzy inference system to predict whether the pedestrian will cross or not. The results offer experimental insights into achieving explainability and interpretability in the pedestrian crossing prediction task.
• Score: 0.47355466227925036
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In the context of autonomous driving, pedestrian crossing prediction is a key component for improving road safety. Presently, the focus of these predictions extends beyond achieving trustworthy results; it is shifting towards the explainability and interpretability of these predictions. This research introduces a novel neuro-symbolic approach that combines deep learning and fuzzy logic for an explainable and interpretable pedestrian crossing prediction. We have developed an explainable predictor (ExPedCross), which utilizes a set of explainable features and employs a fuzzy inference system to predict whether the pedestrian will cross or not. Our approach was evaluated on both the PIE and JAAD datasets. The results offer experimental insights into achieving explainability and interpretability in the pedestrian crossing prediction task. Furthermore, the testing results yield a set of guidelines and recommendations regarding the process of dataset selection, feature selection, and explainability.

Related papers

• Traj-Explainer: An Explainable and Robust Multi-modal Trajectory Prediction Approach [12.60529039445456]
  Navigating complex traffic environments has been significantly enhanced by advancements in intelligent technologies, enabling accurate environment perception and trajectory prediction for automated vehicles. Existing research often neglects the consideration of the joint reasoning of scenario agents and lacks interpretability in trajectory prediction models. An explainability-oriented trajectory prediction model is designed in this work, named Explainable Diffusion Conditional based Multimodal Trajectory Prediction Traj-Explainer.
  arXiv  Detail & Related papers  (2024-10-22T08:17:33Z)
• Sparse Prototype Network for Explainable Pedestrian Behavior Prediction [60.80524827122901]
  We present Sparse Prototype Network (SPN), an explainable method designed to simultaneously predict a pedestrian's future action, trajectory, and pose. Regularized by mono-semanticity and clustering constraints, the prototypes learn consistent and human-understandable features.
  arXiv  Detail & Related papers  (2024-10-16T03:33:40Z)
• Feature Importance in Pedestrian Intention Prediction: A Context-Aware Review [9.475536008455133]
  Recent advancements in predicting pedestrian crossing intentions for Autonomous Vehicles using Computer Vision and Deep Neural Networks are promising. We introduce Context-aware Permutation Feature Importance (CAPFI), a novel approach tailored for pedestrian intention prediction. CAPFI enables more interpretability and reliable assessments of feature importance by leveraging subdivided scenario contexts.
  arXiv  Detail & Related papers  (2024-09-11T22:13:01Z)
• Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction [3.522062800701924]
  We introduce PTINet, which learns trajectory and intention prediction by combining past trajectory observations, local contextual features, and global features. The efficacy of our approach is evaluated on widely used public datasets: JAAD and PIE. PTINet paves the way for the development of automated systems capable of seamlessly interacting with pedestrians in urban settings.
  arXiv  Detail & Related papers  (2024-07-24T11:06:47Z)
• Certified Human Trajectory Prediction [66.1736456453465]
  Tray prediction plays an essential role in autonomous vehicles. We propose a certification approach tailored for the task of trajectory prediction. We address the inherent challenges associated with trajectory prediction, including unbounded outputs, and mutli-modality.
  arXiv  Detail & Related papers  (2024-03-20T17:41:35Z)
• Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach [54.429396802848224]
  This paper proposes an interpretable generative model for motion prediction with robust generalizability to out-of-distribution cases. For interpretability, the model achieves the target-driven motion prediction by estimating the spatial distribution of long-term destinations. Experiments on motion prediction datasets validate that the fitted model can be interpretable and generalizable.
  arXiv  Detail & Related papers  (2024-03-10T04:16:04Z)
• Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information [50.40632021583213]
  Traditional approaches to prediction of future trajectory of road agents rely on knowing information about their past trajectory. This work instead relies on having knowledge of the current state and intended direction to make predictions for multiple vehicles at intersections. Message passing of this information between the vehicles provides each one of them a more holistic overview of the environment.
  arXiv  Detail & Related papers  (2023-01-06T15:13:23Z)
• Behavioral Intention Prediction in Driving Scenes: A Survey [70.53285924851767]
  Behavioral Intention Prediction (BIP) simulates a human consideration process and fulfills the early prediction of specific behaviors. This work provides a comprehensive review of BIP from the available datasets, key factors and challenges, pedestrian-centric and vehicle-centric BIP approaches, and BIP-aware applications.
  arXiv  Detail & Related papers  (2022-11-01T11:07:37Z)
• What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience [63.75363908696257]
  computational reinforcement learning seeks to construct an agent's perception of the world through predictions of future sensations. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. We introduce a meta-gradient descent process by which an agent learns what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward.
  arXiv  Detail & Related papers  (2022-06-13T21:31:06Z)
• Pedestrian Behavior Prediction for Automated Driving: Requirements, Metrics, and Relevant Features [1.1888947789336193]
  We analyze the requirements on pedestrian behavior prediction for automated driving via a system-level approach. Based on human driving behavior we derive appropriate reaction patterns of an automated vehicle. We present a pedestrian prediction model based on a Variational Conditional Auto-Encoder which incorporates multiple contextual cues.
  arXiv  Detail & Related papers  (2020-12-15T16:52:49Z)
• Towards Incorporating Contextual Knowledge into the Prediction of Driving Behavior [5.345872343035626]
  We investigate how predictions are affected by external conditions. More precisely, we investigate how a state-of-the-art approach for lateral motion prediction is influenced by one selected external condition, namely the traffic density. This study constitutes the first step towards the integration of such information into automated vehicles.
  arXiv  Detail & Related papers  (2020-06-15T15:21:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.