Analysis of human-robot spatial behaviour applying a qualitative trajectory calculus

Hanheide, Marc; Peters, Annika; Bellotto, Nicola

doi:10.1109/roman.2012.6343831

Cited by 29 publications

(38 citation statements)

References 15 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key novelty presented in this paper, founded on our previous work on qualitative robot control and human behaviour analysis [1,2], is the combination of coarse and fine QTC representations for a comprehensible ad-hoc definition of HRSIs, which is both flexible and compact. This approach allows for the rapid design of complex spatial behaviours with varying resolution of qualitative description.…”

Section: Rfldo 5rerwlfv /Hfwxuh 1rwhv Lq Andrpsxwhu 6flhqfh 9roxph Ss mentioning

confidence: 99%

“…Initial simulation results using QTC Basic (QTC B ) suggested it was possible to abstract simple human and robot trajectories to generate motion commands based on qualitative terms. The work in [2] extended the spatial behaviours representation to analyse more complex trajectories with QTC Double Cross (QTC C ). To this end, however, no solutions have been implemented that exploit both QTC B and QTC C representations and generate, from real observations, robot control policies within the same qualitative framework.…”

Section: Rfldo 5rerwlfv /Hfwxuh 1rwhv Lq Andrpsxwhu 6flhqfh 9roxph Ss mentioning

confidence: 99%

“…Here we will study two cases that stem from real-world scenarios of robots moving and interacting with people in public spaces (i.e. to approach potential users or share narrow passageways) extending and improving our previous models in [1,2]. The considered HRSIs are not intended to be comprehensive, but just a means to more complex robot behaviours.…”

Section: Application Case Studiesmentioning

confidence: 99%

“…In the second case, we consider a variant of the scenario discussed in [2], where the robot followed predefined trajectories to let a person pass in a narrow corridor, but without reacting to the human movements. Our qualitative approach can encode the same situation, more flexibly, accommodating the situative behaviour of the human.…”

Section: Approach and Avoid (Case Ii)mentioning

confidence: 99%

See 3 more Smart Citations

Qualitative Design and Implementation of Human-Robot Spatial Interactions

2013

Self Cite

View full text Add to dashboard Cite

Abstract. Despite the large number of navigation algorithms available for mobile robots, in many social contexts they often exhibit inopportune motion behaviours in proximity of people, often with very "unnatural" movements due to the execution of segmented trajectories or the sudden activation of safety mechanisms (e.g., for obstacle avoidance). We argue that the reason of the problem is not only the difficulty of modelling human behaviours and generating opportune robot control policies, but also the way human-robot spatial interactions are represented and implemented. In this paper we propose a new methodology based on a qualitative representation of spatial interactions, which is both flexible and compact, adopting the well-defined and coherent formalization of Qualitative Trajectory Calculus (QTC). We show the potential of a QTC-based approach to abstract and design complex robot behaviours, where the desired robot's motion is represented together with its actual performance in one coherent approach, focusing on spatial interactions rather than pure navigation problems.

show abstract

Section: Rfldo 5rerwlfv /Hfwxuh 1rwhv Lq Andrpsxwhu 6flhqfh 9roxph Ss mentioning

confidence: 99%

Section: Rfldo 5rerwlfv /Hfwxuh 1rwhv Lq Andrpsxwhu 6flhqfh 9roxph Ss mentioning

confidence: 99%

Section: Application Case Studiesmentioning

confidence: 99%

Section: Approach and Avoid (Case Ii)mentioning

confidence: 99%

See 2 more Smart Citations

Qualitative Design and Implementation of Human-Robot Spatial Interactions

2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has often been pointed out that mobile robots operating in areas occupied by people will benefit from identification of the human behavior and using this to interact or to avoid interfering with the humans [1], [2], [3]. Ideally the robot will while operating in a new environment be able to learn to make these predictions based on its own observation of the people going about their normal business.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised robot learning to predict person motion

Xiao

Wang

Folkesson

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-Socially interacting robots will need to understand the intentions and recognize the behaviors of people they come in contact with. In this paper we look at how a robot can learn to recognize and predict people's intended path based on its own observations of people over time. Our approach uses people tracking on the robot from either RGBD cameras or LIDAR. The tracks are separated into homogeneous motion classes using a pre-trained SVM. Then the individual classes are clustered and prototypes are extracted from each cluster. These are then used to predict a person's future motion based on matching to a partial prototype and using the rest of the prototype as the predicted motion. Results from experiments in a kitchen environment in our lab demonstrate the capabilities of the proposed method.

show abstract

Vehicle Activity Recognition Using DCNN

AlZoubi

Nam

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

This paper presents a novel Deep Convolutional Neural Network (DCNN) method for vehicle activity classification. We extend our previous approach to be able to classify a larger number of vehicle trajectories in a single network. We also highlight the flexibility of our approach in integrating further scenarios to our classifier. Firstly, a spatiotemporal calculus method is used to encode the relative movement between vehicles as a trajectory of QTC states. We then map the encoded trajectory to a 2D matrix using the one-hot vector mapping, this preserves the important positional data and order for each QTC state. To do this we associate the QTC sequences with pixels to form a 2D image texture. Afterwards, we adapted trained CNN architecture into our vehicles activity recognition task. Two separate types of driving data sets are used to evaluate our method. We demonstrate that the proposed method out-performs existing techniques. Along with the proposed approach we created a new dataset of vehicles interactions. Although the focus of this paper is on the automated analysis of vehicle interactions, the proposed technique is general and can be applied for pairwise analysis for moving objects.

show abstract

Analysis of human-robot spatial behaviour applying a qualitative trajectory calculus

Cited by 29 publications

References 15 publications

Qualitative Design and Implementation of Human-Robot Spatial Interactions

Qualitative Design and Implementation of Human-Robot Spatial Interactions

Unsupervised robot learning to predict person motion

Vehicle Activity Recognition Using DCNN

Contact Info

Product

Resources

About