Corpus ID: 237563066

What we see and What we don't see: Imputing Occluded Crowd Structures from Robot Sensing

  title={What we see and What we don't see: Imputing Occluded Crowd Structures from Robot Sensing},
  author={Javad Amirian and Jean-Bernard Hayet and Julien Pettr{\'e}},
We consider the navigation of mobile robots in crowded environments, for which onboard sensing of the crowd is typically limited by occlusions. We address the problem of inferring the human occupancy in the space around the robot, in blind spots, beyond the range of its sensing capabilities. This problem is rather unexplored in spite of the important impact it has on the robot crowd navigation efficiency and safety, which requires the estimation and the prediction of the crowd state around it… Expand

Figures from this paper

Dreams, maps, and time horizons: exploring hidden forms of student expulsion and disadvantage
ABSTRACT This article explores the idea that effective education policymaking necessitates an improved understanding of how students, as micro-scale actors, position themselves in operational termsExpand


Uncertainty-Aware Occupancy Map Prediction Using Generative Networks for Robot Navigation
A combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments is demonstrated. Expand
Socially-Aware Large-Scale Crowd Forecasting
This work proposes a new descriptor coined as Social Affinity Maps (SAM) to link broken or unobserved trajectories of individuals in the crowd, while using the OD-prior in the authors' framework, and shows improvement in performance through the use of SAM features and OD prior. Expand
You'll never walk alone: Modeling social behavior for multi-target tracking
A model of dynamic social behavior, inspired by models developed for crowd simulation, is introduced, trained with videos recorded from birds-eye view at busy locations, and applied as a motion model for multi-people tracking from a vehicle-mounted camera. Expand
Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes
This paper contributes a new large-scale dataset that collects videos of various types of targets that navigate in a real world outdoor environment such as a university campus and introduces a new characterization that describes the “social sensitivity” at which two targets interact. Expand
A Data-driven Model for Interaction-Aware Pedestrian Motion Prediction in Object Cluttered Environments
This paper introduces a new model based on Long-Short Term Memory (LSTM) neural networks, which is able to learn human motion behavior from demonstrated data and is the first approach using LSTMs, that incorporates both static obstacles and surrounding pedestrians for trajectory forecasting. Expand
Crowds by Example
By learning from real‐world examples, autonomous agents display complex natural behaviors that are often missing in crowd simulations. Expand
Predicting actions to act predictably: Cooperative partial motion planning with maximum entropy models
The approach presented in this paper is based on a feature-based maximum entropy model and is able to guide a robot in an unstructured, real-world environment and is trained to predict joint behavior of heterogeneous groups of agents from onboard data of a mobile platform. Expand
Social LSTM: Human Trajectory Prediction in Crowded Spaces
This work proposes an LSTM model which can learn general human movement and predict their future trajectories and outperforms state-of-the-art methods on some of these datasets. Expand
Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings
A third-order graphical model is proposed that is able to jointly estimate correct trajectories and group memberships over a short time window and a set of experiments underline the importance of joint reasoning for data association in crowded scenarios. Expand
Crowd-11: A Dataset for Fine Grained Crowd Behaviour Analysis
A new deep architecture for crowd characterisation is presented and its application in the context of anomaly classification is demonstrated and expected to be useful in multiple crowd analysis circumstances. Expand