Introducing Probabilistic Bézier Curves for N-Step Sequence Prediction

Hug, Ronny; Hübner, Wolfgang; Arens, Michael

doi:10.1609/aaai.v34i06.6576

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Better prediction results are achievable using a fusion of visual features and coordinate information (Varshneya and Srinivasaraghavan 2017;Xue, Huynh, and Reynolds 2018;Manh and Alaghband 2018;Sadeghian et al 2019;Liang et al 2019;Kosaraju et al 2019;Sun, Zhao, and He 2020;Dendorfer, Elflein, and Leal-Taixé 2021;Zhao et al 2019;Tao, Jiang, and Duan 2020;Sun, Jiang, and Lu 2020;Shafiee, Padir, and Elhamifar 2021;Chai et al 2019). Recently, the use of Gaussian distribution (Hug, Hübner, and Arens 2020;Hug et al 2022;Xu, Yang, and Du 2020), generative adversarial networks (GANs) (Gupta et al 2018;Sadeghian et al 2019;Kosaraju et al 2019;Li 2019;Dendorfer, Elflein, and Leal-Taixé 2021) and the Conditional Variational Auto-encoder (CVAE) (Lee et al 2017;Ivanovic and Pavone 2019;Salzmann et al 2020;Chen et al 2021b;Yao et al 2021;Xu et al 2022a;Wang et al 2022;Yue, Manocha, and Wang 2022;Xu, Hayet, and Karamouzas 2022;Wen, Wang, and Metaxas 2022) are proposed to infer socially-acceptable multiple trajectories.…”

Section: Related Workmentioning

confidence: 99%

A Set of Control Points Conditioned Pedestrian Trajectory Prediction

Bae

Jeon

2023

AAAI

View full text Add to dashboard Cite

Predicting the trajectories of pedestrians in crowded conditions is an important task for applications like autonomous navigation systems. Previous studies have tackled this problem using two strategies. They (1) infer all future steps recursively, or (2) predict the potential destinations of pedestrians at once and interpolate the intermediate steps to arrive there. However, these strategies often suffer from the accumulated errors of the recursive inference, or restrictive assumptions about social relations in the intermediate path. In this paper, we present a graph convolutional network-based trajectory prediction. Firstly, we propose a control point prediction that divides the future path into three sections and infers the intermediate destinations of pedestrians to reduce the accumulated error. To do this, we construct multi-relational weighted graphs to account for their physical and complex social relations. We then introduce a trajectory refinement step based on a spatio-temporal and multi-relational graph. By considering the social interactions between neighbors, better prediction results are achievable. In experiments, the proposed network achieves state-of-the-art performance on various real-world trajectory prediction benchmarks.

show abstract

Section: Related Workmentioning

confidence: 99%

A Set of Control Points Conditioned Pedestrian Trajectory Prediction

Bae

Jeon

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Hug et al [26] introduced the concept of probabilistic Bézier curves. A probabilistic curve is defined not by a fixed set of control points, but by a set of mutually-independent Gaussian distributions over each control point, where each Gaussian vector is defined by a mean, C i ∈ R d , and a covariance matrix, Σ i ∈ R d×d .…”

Section: Probabilistic B èZier Curvesmentioning

confidence: 99%

This is the Way: Differential Bayesian Filtering for Agile Trajectory Synthesis

Weiss

Behl

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

One of the main challenges in autonomous racing is to design algorithms for motion planning at high speed, and across complex racing courses. End-to-end trajectory synthesis has been previously proposed where the trajectory for the ego vehicle is computed based on camera images from the racecar. This is done in a supervised learning setting using behavioral cloning techniques. In this paper, we address the limitations of behavioral cloning methods for trajectory synthesis by introducing Differential Bayesian Filtering (DBF), which uses probabilistic Bézier curves as a basis for inferring optimal autonomous racing trajectories based on Bayesian inference. We introduce a trajectory sampling mechanism and combine it with a filtering process which is able to push the car to its physical driving limits. The performance of DBF is evaluated on the DeepRacing Formula One simulation environment and compared with several other trajectory synthesis approaches as well as human driving performance. DBF achieves the fastest lap time, and the fastest speed, by pushing the racecar closer to its limits of control while always remaining inside track bounds.

show abstract

“…However, capturing the multi-modality of trajectory prediction is out of the scope of this paper. For example, this component can be replaced by flow -based models [9] or N -curve models [17].…”

Section: Missformermentioning

confidence: 99%

MissFormer: (In-)Attention-Based Handling of Missing Observations for Trajectory Filtering and Prediction

Becker

Hug

Hübner

et al. 2021

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learningbased models for various sequence learning tasks, these models increasingly replace classic approaches in object tracking applications for inferring the objects' motion states. While traditional tracking approaches can deal with missing observations, most of their deep counterparts are, by default, not suited for this. Towards this end, this paper introduces a transformer -based approach for handling missing observations in variable input length trajectory data. The model is formed indirectly by successively increasing the complexity of the demanded inference tasks. Starting from reproducing noise-free trajectories, the model then learns to infer trajectories from noisy inputs. By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs. In the case of a sequence of successive missing events, the model then acts as a pure prediction model. The abilities of the approach are demonstrated on synthetic data and real-world data reflecting prototypical object tracking scenarios.

show abstract

Introducing Probabilistic Bézier Curves for N-Step Sequence Prediction

Cited by 6 publications

References 9 publications

A Set of Control Points Conditioned Pedestrian Trajectory Prediction

A Set of Control Points Conditioned Pedestrian Trajectory Prediction

This is the Way: Differential Bayesian Filtering for Agile Trajectory Synthesis

MissFormer: (In-)Attention-Based Handling of Missing Observations for Trajectory Filtering and Prediction

Contact Info

Product

Resources

About