Context-Aware Trajectory Prediction

Bartoli, Federico; Lisanti, Giuseppe; Ballan, Lamberto; Bimbo, Alberto Del

doi:10.1109/icpr.2018.8545447

Cited by 147 publications

(125 citation statements)

References 25 publications

(49 reference statements)

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…These frameworks facilitate reasoning about collaboration strategies, but suffer from "state space explosion" intractability except when interactions are known to be sparse [24] or hierarchically decomposable [11]. Multi-agent Forecasting: Data-driven approaches have been applied to forecast complex interactions between multiple pedestrians [1,3,10,14,21], vehicles [6,19,26], and athletes [9,18,20,32,34,35]. These methods attempt to generalize from previously observed interactions to predict multi-agent behavior in new situations.…”

Section: Related Workmentioning

confidence: 99%

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

Rhinehart

McAllister

Kitani

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

320

236

View full text Add to dashboard Cite

For autonomous vehicles (AVs) to behave appropriately on roads populated by human-driven vehicles, they must be able to reason about the uncertain intentions and decisions of other drivers from rich perceptual information. Towards these capabilities, we present a probabilistic forecasting model of future interactions of multiple agents. We perform both standard forecasting and conditional forecasting with respect to the AV's goals. Conditional forecasting reasons about how all agents will likely respond to specific decisions of a controlled agent. We train our model on real and simulated data to forecast vehicle trajectories given past positions and LIDAR. Our evaluation shows that our model is substantially more accurate in multi-agent driving scenarios compared to existing state-of-the-art. Beyond its general ability to perform conditional forecasting queries, we show that our model's predictions of all agents improve when conditioned on knowledge of the AV's intentions, further illustrating its capability to model agent interactions.

show abstract

Section: Related Workmentioning

confidence: 99%

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

Rhinehart

McAllister

Kitani

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

320

236

View full text Add to dashboard Cite

show abstract

“…They select the most reasonable trajectories by scoring them based on future interactions and consider the environment by encoding an occupancy grid map with a Convolutional Neural Network. Bartoli et al [26] consider environmental context by providing an LSTM with distances of the target pedestrian to static objects in space, as well as a human-to-human context in form of a grid map, or alternatively the neighbors' hidden encodings. Pfeiffer et al [27] propose an LSTM that receives static obstacles as an occupancy grid and surrounding pedestrians as an angular grid.…”

Section: Related Workmentioning

confidence: 99%

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

Schöller

Aravantinos

Lay

et al. 2020

IEEE Robot. Autom. Lett.

199

120

View full text Add to dashboard Cite

Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that -surprisingly -a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as relevant as commonly believed. Therefore, we analyze how neural networks process their input and how it impacts their predictions. Our analysis reveals pitfalls in training neural networks for pedestrian motion prediction and clarifies false assumptions about the problem itself. In particular, neural networks implicitly learn environmental priors that negatively impact their generalization capability, the motion history of pedestrians is irrelevant and interactions are too complex to predict. Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.

show abstract

“…As a strategy to extract the relevant variables for behavior, we have required them to predict future behavior (like e.g. [32,33,25,20]). This approach has the additional advantage of automatically generating labelled data for supervised training of networks.…”

Section: Discussionmentioning

confidence: 99%

Deep attention networks reveal the rules of collective motion in zebrafish

Heras

Romero-Ferrero

Hinz

et al. 2018

Preprint

View full text Add to dashboard Cite

A variety of simple models has been proposed to understand the collective motion of animals. These models can be insightful but lack important elements necessary to predict the motion of each individual in the collective. Adding more detail increases predictability but can make models too complex to be insightful. Here we report that deep attention networks can obtain in a data-driven way a model of collective behavior that is simultaneously predictive and insightful thanks to an organization in modules. The model obtains that interactions between two zebrafish, Danio rerio, in a large groups of 60-100, can be approximately be described as repulsive, attractive or as alignment, but only when moving slowly. At high velocities, interactions correspond only to alignment or alignment mixed with repulsion at close distances. The model also shows that each zebrafish decides where to move by aggregating information from the group as a weighted average over neighbours. Weights are higher for neighbours that are close, in a collision path or moving faster in frontal and lateral locations. These weights effectively select 5 relevant neighbours on average, but this number is dynamical, changing between a single neighbour to up to 12, often in less than a second. Our results suggest that each animal in a group decides by dynamically selecting information from the group. Highlights• At 30 days postfertilization, zebrafish, Danio rerio, can move in very cohesive and predictable large groups• Deep attention networks obtain a predictive and understadable model of collective motion• When moving slowly, interations between pairs of zebrafish have clear components of repulsion, attraction and alignment• When moving fast, interactions correspond to alignment and a mixture of alignment and repulsion at close distances • Zebrafish turn left or right depending on a weighted average of interaction information with other fish, with weights higher for close fish, those in a collision path or those moving fast in front or to the sides • Aggregation is dynamical, oscillating between 1 and 12 neighbouring fish, with 5 on average

show abstract

Context-Aware Trajectory Prediction

Cited by 147 publications

References 25 publications

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

Deep attention networks reveal the rules of collective motion in zebrafish

Contact Info

Product

Resources

About