Exploring Attention GAN for Vehicle Motion Prediction

Abstract

Motion Prediction (MP) of multiple surroundings agents is a crucial task in arbitrarily complex environments, from simple robots to Autonomous Driving Stacks (ADS). Current techniques tackle this problem using end-to-end pipelines, where the input data is usually a rendered top-view of the physical information and the past trajectories of the most relevant agents; leveraging this information is a must to obtain optimal performance. In that sense, a reliable ADS must produce reasonable predictions on time. However, despite many approaches use simple ConvNets and LSTMs to obtain the social latent features, State-Of-The-Art (SOTA) models might be too complex for realtime applications when using both sources of information (map and past trajectories) as well as little interpretable, specially considering the physical information. Moreover, the performance of such models highly depends on the number of available inputs for each particular traffic scenario, which are expensive to obtain, particularly, annotated High-Definition (HD) maps.In this work, we propose several efficient baselines for the well-known Argoverse 1 Motion Forecasting Benchmark. We aim to develop compact models using SOTA techniques for MP, including attention mechanisms and GNNs. Our lightweight models use standard social information and interpretable map information such as points from the driveable area and plausible centerlines by means of a novel preprocessing step based on kinematic constraints, in opposition to black-box CNN-based or toocomplex graphs methods for map encoding, to generate plausible multimodal trajectories achieving up-to-pair accuracy with less operations and parameters than other SOTA methods. Our code is publicly available at https://github.com/Cram3r95/mapfe4mp.

Self-Evaluation of Trajectory Predictors for Autonomous Driving

“…The results show that uncertainty has potential for failure detection in motion prediction. Gomez-Huelamo et al [30] propose a prediction method that combines deep learning with heuristic scenario understanding to achieve accurate trajectory forecasting. Attention mechanisms with GNNs are used to enhance the interactions among objects.…”

Analysis and Enhancement of Resilience for LSTM Accelerators Using Residue-Based CEDs

“…The most commonly used RNN is Long Short-Term Memory (LSTM) [1], which can learn the longterm dependencies in input sequences, providing high accuracy. LSTM networks have demonstrated great effectiveness in real-time safety-critical sequence processing tasks, such as robotics [3], healthcare devices [4], and autonomous driving [5].…”