Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction

Thiede, Luca Anthony; Brahma, Pratik Prabhanjan

doi:10.1109/iccv.2019.01005

Cited by 48 publications

(28 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several recently introduced metrics follow a sampling approach to evaluate a probability distribution. The minimum average displacement error (mADE) metric (Rhinehart et al, 2019; Schöller et al, 2019; Tang and Salakhutdinov, 2019; Thiede and Brahma, 2019; Walker et al, 2016), as well as variety loss, oracle, minimum over N , best-of- N , top n% , or minimum mean squared distance (minMSD), computes Euclidean distance between the ground-truth position of the agent s t * at time t and the closest (or the n % closest) of the K samples from the predicted probability distribution: min k ∥ s t * − s t k ∥ . Similarly, minimum final displacement error (mFDE) evaluates only the distribution at the prediction horizon T .…”

Section: Motion Prediction Evaluationmentioning

confidence: 99%

Human motion trajectory prediction: a survey

Rudenko

Palmieri

Herman³

et al. 2020

The International Journal of Robotics Research

611

306

View full text Add to dashboard Cite

With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand, and anticipate human behavior becomes increasingly important. Specifically, predicting future positions of dynamic agents and planning considering such predictions are key tasks for self-driving vehicles, service robots, and advanced surveillance systems. This article provides a survey of human motion trajectory prediction. We review, analyze, and structure a large selection of work from different communities and propose a taxonomy that categorizes existing methods based on the motion modeling approach and level of contextual information used. We provide an overview of the existing datasets and performance metrics. We discuss limitations of the state of the art and outline directions for further research.

show abstract

Section: Motion Prediction Evaluationmentioning

confidence: 99%

Human motion trajectory prediction: a survey

Rudenko

Palmieri

Herman³

et al. 2020

The International Journal of Robotics Research

611

306

View full text Add to dashboard Cite

show abstract

“…Simultaneously, Refs. [14,15,20] also proposed probability networks to incorporate randomness into vehicle trajectory prediction. However, these works all treat position information as two-dimensional point coordinates for input into the prediction model; doing so cannot completely describe the random behavior of pedestrians.…”

Section: Multi-outcome Trajectory Forecastingmentioning

confidence: 99%

Trajectory distributions: A new description of movement for trajectory prediction

Wei

et al. 2021

Comp. Visual Media

View full text Add to dashboard Cite

Trajectory prediction is a fundamental and challenging task for numerous applications, such as autonomous driving and intelligent robots. Current works typically treat pedestrian trajectories as a series of 2D point coordinates. However, in real scenarios, the trajectory often exhibits randomness, and has its own probability distribution. Inspired by this observation and other movement characteristics of pedestrians, we propose a simple and intuitive movement description called a trajectory distribution, which maps the coordinates of the pedestrian trajectory to a 2D Gaussian distribution in space. Based on this novel description, we develop a new trajectory prediction method, which we call the social probability method. The method combines trajectory distributions and powerful convolutional recurrent neural networks. Both the input and output of our method are trajectory distributions, which provide the recurrent neural network with sufficient spatial and random information about moving pedestrians. Furthermore, the social probability method extracts spatio-temporal features directly from the new movement description to generate robust and accurate predictions. Experiments on public benchmark datasets show the effectiveness of the proposed method.

show abstract

“…To account for uncertainty and multi-modality in prediction space, generative adversarial networks (GAN) [17] and variational autoencoders (VAE) [18], [19] are used to generate multiple trajectory predictions by sampling a latent space. Several works have attempted to improve coverage of the possible outcomes [1], [3], [20], [21], yet there is an inherent tradeoff between accurately representing the trajectory distribution and covering a diverse set of intents [1], [2], [3]. To account for this trade-off between accuracy and coverage explicitly, hybrid models are proposed to classify discrete intent and generate continuous trajectories conditioned on the intent.…”

Section: Related Workmentioning

confidence: 99%

“…Given a set of observed discrete-continuous future agent states O = (O x , O z ) 2 and context states C, we want to learn a hybrid model parameterized by θ that maximizes the following data log likelihood [31], as a maximum likelihood 2 While the continuous state can be directly observed from perception systems, the discrete observation can be estimated from continuous observations, as discussed in Sec. III-A.…”

Section: B Hybrid Model Learningmentioning

confidence: 99%

See 1 more Smart Citation

HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling

Huang¹,

Rosman²,

Gilitschenski³

et al. 2021

Preprint

View full text Add to dashboard Cite

Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid prediction framework that models evolving human intent. By modeling traffic agents as a hybrid discretecontinuous system, our approach is capable of predicting discrete intent changes over time. We learn the probabilistic hybrid model via a maximum likelihood estimation problem and leverage neural proposal distributions to sample adaptively from the exponentially growing discrete space. The overall approach affords a better trade-off between accuracy and coverage. We train and validate our model on the Argoverse dataset, and demonstrate its effectiveness through comprehensive ablation studies and comparisons with state-of-the-art models.

show abstract

Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction

Cited by 48 publications

References 21 publications

Human motion trajectory prediction: a survey

Human motion trajectory prediction: a survey

Trajectory distributions: A new description of movement for trajectory prediction

HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling

Contact Info

Product

Resources

About