Context-Aware Trajectory Prediction

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

doi:10.48550/arxiv.1705.02503

Cited by 12 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, [1] used Long Short-Term Memory networks (LSTM) to model the joint distribution of future trajectories of interacting agents. This work has been extended in [2], [29] to include static obstacles in the model in addition to dynamic agents. However, these approaches assume that only the dynamic agents in a local discretized neighborhood of a pedestrian affect the pedestrian's motion.…”

Section: B Human Trajectory Predictionmentioning

confidence: 99%

Social Attention: Modeling Attention in Human Crowds

Vemula

Muelling

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

599

469

View full text Add to dashboard Cite

Robots that navigate through human crowds need to be able to plan safe, efficient, and human predictable trajectories. This is a particularly challenging problem as it requires the robot to predict future human trajectories within a crowd where everyone implicitly cooperates with each other to avoid collisions. Previous approaches to human trajectory prediction have modeled the interactions between humans as a function of proximity. However, that is not necessarily true as some people in our immediate vicinity moving in the same direction might not be as important as other people that are further away, but that might collide with us in the future. In this work, we propose Social Attention, a novel trajectory prediction model that captures the relative importance of each person when navigating in the crowd, irrespective of their proximity. We demonstrate the performance of our method against a state-of-the-art approach on two publicly available crowd datasets and analyze the trained attention model to gain a better understanding of which surrounding agents humans attend to, when navigating in a crowd.

show abstract

Section: B Human Trajectory Predictionmentioning

confidence: 99%

Social Attention: Modeling Attention in Human Crowds

Vemula

Muelling

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

599

469

View full text Add to dashboard Cite

show abstract

“…The main disadvantage of these models is the need to hand-craft rules and features, limiting their ability to efficiently learn beyond abstract level and the domain experts. Modern socially-aware trajectory prediction work usually use recurrent neural networks [1,14,6,5,4,11]. Hug et al [10] present an experiment-based study the effectiveness of some RNN models in the context socially aware trajectory prediction.…”

Section: Related Workmentioning

confidence: 99%

“…Few recent approaches [14,26,4], to some extent, incorporate both the scene and social factors into their models. However, these models only consider the interaction among the limited adjacent agents and are only able to generate a single plausible path for each agent.…”

Section: Related Workmentioning

confidence: 99%

SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints

Sadeghian

Kosaraju

Sadeghian

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

821

798

View full text Add to dashboard Cite

This paper addresses the problem of path prediction for multiple interacting agents in a scene, which is a crucial step for many autonomous platforms such as self-driving cars and social robots. We present SoPhie; an interpretable framework based on Generative Adversarial Network (GAN), which leverages two sources of information, the path history of all the agents in a scene, and the scene context information, using images of the scene. To predict a future path for an agent, both physical and social information must be leveraged. Previous work has not been successful to jointly model physical and social interactions. Our approach blends a social attention mechanism with a physical attention that helps the model to learn where to look in a large scene and extract the most salient parts of the image relevant to the path. Whereas, the social attention component aggregates information across the different agent interactions and extracts the most important trajectory information from the surrounding neighbors. SoPhie also takes advantage of GAN to generates more realistic samples and to capture the uncertain nature of the future paths by modeling its distribution. All these mechanisms enable our approach to predict socially and physically plausible paths for the agents and to achieve state-of-the-art performance on several different trajectory forecasting benchmarks.

show abstract

“…LSTMs have been very popular due to time series processing. Initial works exploited LSTMs for trajectories to model the interaction between objects [2,59,65], for scenes to exploit the semantics [4,38], and LSTMs with attention to focus on the relevant semantics [46].…”

Section: Related Workmentioning

confidence: 99%

“…The environment poses constraints for objects during navigation. While some recent works use an LSTM to learn environment constraints from images [38,60], others [4,12] choose a more explicit approach by dividing the environment into meaningful grids to learn the grid-grid, object-object and object-grid interactions. Also soft attention mechanisms are commonly used to focus on relevant features of the environments [45,46].…”

Section: Related Workmentioning

confidence: 99%

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior

Makansi¹,

Çiçek²,

Buchicchio³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, we investigate the problem of anticipating future dynamics, particularly the future location of other vehicles and pedestrians, in the view of a moving vehicle. We approach two fundamental challenges: (1) the partial visibility due to the egocentric view with a single RGB camera and considerable field-of-view change due to the egomotion of the vehicle; (2) the multimodality of the distribution of future states. In contrast to many previous works, we do not assume structural knowledge from maps. We rather estimate a reachability prior for certain classes of objects from the semantic map of the present image and propagate it into the future using the planned egomotion. Experiments show that the reachability prior combined with multi-hypotheses learning improves multimodal prediction of the future location of tracked objects and, for the first time, the emergence of new objects. We also demonstrate promising zero-shot transfer to unseen datasets.

show abstract

Context-Aware Trajectory Prediction

Cited by 12 publications

References 0 publications

Social Attention: Modeling Attention in Human Crowds

Social Attention: Modeling Attention in Human Crowds

SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior

Contact Info

Product

Resources

About