SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

Liang, Junwei; Jiang, Lu; Hauptmann, Alexander G.

doi:10.48550/arxiv.2004.02022

Cited by 8 publications

(4 citation statements)

References 90 publications

(192 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We demonstrate that our NSP model outperforms the state-of-the-art methods [18,49,9,29,33,14,31,38,50,32,37,56,77,16,71] in standard trajectory prediction tasks across various benchmark datasets [46,43,28] and metrics. In addition, we show that NSP can generalize to unseen scenarios with higher densities and still predict plausible motions with less collision between people, as opposed to pure black-box deep learning approaches.…”

Section: Introductionmentioning

confidence: 91%

“…Following prior works, in the presence of multiple possible future predictions, the minimal error is reported. We compare our NSP-SFM with an extensive list of baselines, including published papers and unpublished technical reports: Social GAN (S-GAN) [18], Sophie [49], Conditional Flow VAE (CF-VAE) [9], Conditional Generative Neural System (CGNS) [29], NEXT [33], P2TIRL [14], SimAug [31], PECNet [38], Traj++ [50], Multiverse [32], Y-Net [37], SIT [56], S-CSR [77], Social-DualCVAE [16] and CSCNet [71]. We divide the baselines into two groups due to their setting differences.…”

Section: Trajectory Predictionmentioning

confidence: 99%

“…a linear dynamical system [19], but retains sufficient flexibility so that the model can be adjusted to fit observations. More recently, model-free methods based on deep learning have also been explored, and these demonstrate surprising trajectory prediction capability [1,18,49,9,29,33,14,31,38,50,32,37,56,77,16,71].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human Trajectory Prediction via Neural Social Physics

Yue¹,

Manocha²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

Trajectory prediction has been widely pursued in many fields, and many model-based and model-free methods have been explored. The former include rule-based, geometric or optimization-based models, and the latter are mainly comprised of deep learning approaches. In this paper, we propose a new method combining both methodologies based on a new Neural Differential Equation model. Our new model (Neural Social Physics or NSP) is a deep neural network within which we use an explicit physics model with learnable parameters. The explicit physics model serves as a strong inductive bias in modeling pedestrian behaviors, while the rest of the network provides a strong data-fitting capability in terms of system parameter estimation and dynamics stochasticity modeling. We compare NSP with 15 recent deep learning methods on 6 datasets and improve the state-of-the-art performance by 5.56%-70%. Besides, we show that NSP has better generalizability in predicting plausible trajectories in drastically different scenarios where the density is 2-5 times as high as the testing data. Finally, we show that the physics model in NSP can provide plausible explanations for pedestrian behaviors, as opposed to black-box deep learning. Code is available: https://github.com/realcrane/Human-Trajectory-Prediction-via-Neural-Social-Physics.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Trajectory Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Human Trajectory Prediction via Neural Social Physics

Yue¹,

Manocha²,

Wang³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…NMMP [22] models the directed interaction with the neural motion message passing strategy. SimAug [26] is trained only on 3D simulation data to predict future trajectories. LB-EBM [30] is a probabilistic model with cost function defined in the latent space to account for the movement history and social context for diverse human trajectories.…”

Section: Experimental Evaluationmentioning

confidence: 99%

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

Zhang¹,

Wang²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

A profound understanding of inter-agent relationships and motion behaviors is important to achieve high-quality planning when navigating in complex scenarios, especially at urban traffic intersections. We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space. Specifically, the SDG is used to capture spatial interactions by reconstructing sub-graphs for different agents with dynamic and changeable characteristics during each frame. The BDG is used to infer motion tendency by modeling the implicit dependency of the current state on priors behaviors, especially the discontinuous motions corresponding to acceleration, deceleration, or turning direction. Moreover, we present a new dataset for vehicle trajectory prediction under traffic lights called VTP-TL. Our experimental results show that our model achieves more than 20.45% and 20.78% improvement in terms of ADE and FDE, respectively, on VTP-TL as compared to other trajectory prediction algorithms. The dataset and code are available at: https://github.com/VTP-TL/D2-TPred.

show abstract