Predicting Occupancy Distributions of Walking Humans With Convolutional Neural Networks

Doellinger, Johannes; Spies, Markus; Burgard, Wolfram

doi:10.1109/lra.2018.2800780

Cited by 15 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The term robot-of-human transparency is not widely used in literature. However, examples of robot-of-human transparency, without using the term directly, can be found in Lorenz et al ( 2014 ); Lorenz ( 2015 ); Tsiourti and Weiss ( 2014 ); Dragan ( 2017 ); Wang et al ( 2017 ); Doellinger et al ( 2018 ); Goldhoorn et al ( 2018 ); Gui et al ( 2018 ), and Javdani et al ( 2018 ). In Casalino et al ( 2018 ) and Chang et al ( 2018 ) a feedback of the intent recognition is communicated to the operator.…”

Section: Transparency As Observability and Predictability Of The Smentioning

confidence: 99%

System Transparency in Shared Autonomy: A Mini Review

Alonso

Puente

2018

Front. Neurorobot.

View full text Add to dashboard Cite

What does transparency mean in a shared autonomy framework? Different ways of understanding system transparency in human-robot interaction can be found in the state of the art. In one of the most common interpretations of the term, transparency is the observability and predictability of the system behavior, the understanding of what the system is doing, why, and what it will do next. Since the main methods to improve this kind of transparency are based on interface design and training, transparency is usually considered a property of such interfaces, while natural language explanations are a popular way to achieve transparent interfaces. Mechanical transparency is the robot capacity to follow human movements without human-perceptible resistive forces. Transparency improves system performance, helping reduce human errors, and builds trust in the system. One of the principles of user-centered design is to keep the user aware of the state of the system: a transparent design is a user-centered design. This article presents a review of the definitions and methods to improve transparency for applications with different interaction requirements and autonomy degrees, in order to clarify the role of transparency in shared autonomy, as well as to identify research gaps and potential future developments.

show abstract

Section: Transparency As Observability and Predictability Of The Smentioning

confidence: 99%

System Transparency in Shared Autonomy: A Mini Review

Alonso

Puente

2018

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…On this basis, the target collision time can be estimated to remind the vehicle to avoid. Doellinger [25] used CNN to predict average occupancy maps of walking humans even in environments where information about trajectory is not available. However, pedestrian trajectory prediction is a complex task because humans may change directions suddenly depending on objects, vehicles, human interaction, etc.…”

Section: Related Workmentioning

confidence: 99%

Prediction of Pedestrian Crossing Behavior Based on Surveillance Video

Zhou

Ren

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Prediction of pedestrian crossing behavior is an important issue faced by the realization of autonomous driving. The current research on pedestrian crossing behavior prediction is mainly based on vehicle camera. However, the sight line of vehicle camera may be blocked by other vehicles or the road environment, making it difficult to obtain key information in the scene. Pedestrian crossing behavior prediction based on surveillance video can be used in key road sections or accident-prone areas to provide supplementary information for vehicle decision-making, thereby reducing the risk of accidents. To this end, we propose a pedestrian crossing behavior prediction network for surveillance video. The network integrates pedestrian posture, local context and global context features through a new cross-stacked gated recurrence unit (GRU) structure to achieve accurate prediction of pedestrian crossing behavior. Applied onto the surveillance video dataset from the University of California, Berkeley to predict the pedestrian crossing behavior, our model achieves the best results regarding accuracy, F1 parameter, etc. In addition, we conducted experiments to study the effects of time to prediction and pedestrian speed on the prediction accuracy. This paper proves the feasibility of pedestrian crossing behavior prediction based on surveillance video. It provides a reference for the application of edge computing in the safety guarantee of automatic driving.

show abstract

“…To increase the tracking accuracy of pedestrians, the model can provide important information based on predicted pedestrian walking paths. Doellinger et al [90] used CNN to predict average occupancy maps of walking humans even in environments where information about trajectory is not available. Their method is reported to perform better than several baseline methods.…”

Section: Trajectory Prediction Based On Convolutional Neural Networkmentioning

confidence: 99%

A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction

Sighencea

Stanciu

Căleanu

2021

Sensors

View full text Add to dashboard Cite

Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions.

show abstract

Predicting Occupancy Distributions of Walking Humans With Convolutional Neural Networks

Cited by 15 publications

References 16 publications

System Transparency in Shared Autonomy: A Mini Review

System Transparency in Shared Autonomy: A Mini Review

Prediction of Pedestrian Crossing Behavior Based on Surveillance Video

A Review of Deep Learning-Based Methods for Pedestrian Trajectory Prediction

Contact Info

Product

Resources

About