Artificial Intelligence for Vehicle Behavior Anticipation: Hybrid Approach Based on Maneuver Classification and Trajectory Prediction
TL;DR: A hybrid approach to integrate maneuver classification using neural networks and trajectory prediction using Long Short-term Memory (LSTM) networks to get the future positions of adjacent vehicles to demonstrate a high performance compared to various existing methods.
read more
Abstract: Innovative technologies and naturalistic driving data sources provide a great potential to develop reliable autonomous driving systems. Understanding the behaviors of surrounding vehicles is essential for improving safety and mobility of autonomous vehicles. Onboard sensors like Radar, Lidar and Camera are able to track surrounding vehicles motion and to get different features like position, velocity and yaw. This paper proposes a hybrid approach to integrate maneuver classification using neural networks and trajectory prediction using Long Short-term Memory (LSTM) networks to get the future positions of adjacent vehicles. In this study we use the Next Generation Simulation (NGSIM) public dataset that provides a real driving data. The proposed approach is validated experimentally using VEDECOM demonstrator data. The results demonstrate that the proposed approach is able to predict driver intention to change lanes on average 2.2 seconds in advance. The Root Mean Square (RMS) errors of lateral and longitudinal positions are 0.30 m and 3.1 m respectively. The results demonstrate a high performance compared to various existing methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles
TL;DR: A three-step decision-making method was developed: trajectory prediction of the surrounding vehicles, risk and gain computation associated with the maneuver and based on the predicted trajectories, and finally decision making.
Improving Efficiency and Generalisability of Motion Predictions With Deep Multi-Agent Learning and Multi-Head Attention
Djamel Eddine Benrachou,Sebastien Glaser,Mohammed Elhenawy,Andry Rakotonirainy +3 more
TL;DR: This study proposes a deep multi-agent learning-based framework for predicting the future intentions and trajectories of surrounding vehicles in freeway operation, achieving lower prediction error and higher generalisability than state-of-the-art approaches using real traffic data and datasets.
4
Lane Change Decision Algorithm based on Risk Prediction and Fuzzy Logic Method
Amin Mechernene,Vincent Judalet,Ahmed Chaibet,Moussa Boukhnifer +3 more
- 20 Oct 2021
TL;DR: In this paper, a decision algorithm for lane changing in highways and arterial road is elaborated, which consists of a risk assessment based on predicted trajectories to determine the optimal moment to start the maneuver.
3
A Review on Intention-aware and Interaction-aware Trajectory Prediction for Autonomous Vehicles
16 Mar 2022
TL;DR: A literature review on intention-aware and interaction-aware trajectory prediction for autonomous vehicles is presented in this article , where the authors try to understand how intention/interaction improves prediction, and what are the techniques and technologies employed in trajectory prediction.
3
Short-Term Lateral Behavior Reasoning for Target Vehicles Considering Driver Preview Characteristic
TL;DR: Wang et al. as discussed by the authors proposed a driver preview and multiple centerline model-based probabilistic behavior recognition architecture for timely and accurate TV lateral behavior prediction, where the preview lateral offset and preview lateral velocity are combined with multiple centreline model for TV lateral behaviour reasoning.
References
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
•Posted Content
Empirical evaluation of gated recurrent neural networks on sequence modeling
TL;DR: These advanced recurrent units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU), are found to be comparable to LSTM.
14.1K
A survey on motion prediction and risk assessment for intelligent vehicles
TL;DR: This paper points out the tradeoff between model completeness and real-time constraints, and the fact that the choice of a risk assessment method is influenced by the selected motion model.
An LSTM network for highway trajectory prediction
Florent Altché,Arnaud de La Fortelle +1 more
- 16 Oct 2017
TL;DR: This article presents a first step towards consistent trajectory prediction by introducing a long short-term memory (LSTM) neural network, which is capable of accurately predicting future longitudinal and lateral trajectories for vehicles on highway.
710