Real-time collision detection and distance computation on point cloud sensor data

Pan, Jia; Sucan, Ioan A.; Chitta, Sachin; Manocha, Dinesh

doi:10.1109/icra.2013.6631081

Cited by 30 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, contact points scattered on a plane can safely be reduced to their convex hull without any loss of accuracy in contact response. Another possibility is to incorporate methods for accelerating BLEM contact detection with large meshes or point cloud data sets [18], possibly using GPUs. Finally, it may be possible to develop methods that adapt boundary thickness and time stepping dynamically to support collisions between very thin objects, or to employ fallback methods that retract meshes out of collision once boundary layers are penetrated.…”

Section: Resultsmentioning

confidence: 99%

Robust Contact Generation for Robot Simulation with Unstructured Meshes

Hauser

2016

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

This paper presents a numerically stable method for rigid body simulation of unstructured meshes undergoing forceful contact, such as in robot locomotion and manipulation. The key contribution is a new contact generation method that treats the geometry as having a thin virtual boundary layer around the underlying meshes. Unlike existing methods, it produces contact estimates that are stable with respect to small displacements, which helps avoid jitter or divergence in the simulator caused by oscillatory discontinuities. Its advantages are particularly apparent on non-watertight meshes and can easily simulate interaction with partially-sensed and noisy objects, such as those that emerge from low-cost 3D scanners. The simulator is tested on a variety of robot locomotion and manipulation examples, and results closely match theoretical predictions and experimental data.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust Contact Generation for Robot Simulation with Unstructured Meshes

Hauser

2016

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…Videos of a human crowd have been used to calibrate simulated crowd density (Pelechano, Allbeck, & Badler, 2008). GAMMA research group located in UNC is an active group that models live crowd models (Pan, Sucan, Chitta, & Manocha, 2013).…”

Section: Crowdsmentioning

confidence: 99%

Crowd dynamics of behavioural intention: train station and museum case studies

2014

View full text Add to dashboard Cite

As the human population grows so does the need to understand human behaviour. One particularly important aspect of human behaviour is how it changes within conglomerations of people (i.e. crowds). In this article, a method for modelling crowd behaviour is proposed. This method draws inspiration from the concept of behavioural intention and the related forces of attitudes, influences, and social norms. These topics are first defined and detailed, followed by a survey of related research. Next, the model is presented and adapted to two common crowd dynamic scenarios, which stress a component of behavioural intention. Finally, observations are made about the model, as well as extensions to the models and directions for future research are considered. IntroductionThe capacity to predict and better understand human behaviour is a powerful tool for improving nearly any computational endeavour that involves human interaction such as architecture design, evacuation planning, crowd control, or disaster response. As the human population has grown in number and spread across the planet, so has the opportunity for humanity to demonstrate special forms of behaviour observed when masses of people gather together and form crowds. Crowd studies have been further augmented by the maturation of the social and psychological sciences and by the development of computer technology powerful enough for modelling and simulation.Alongside contributing factors such as industrialisation and the rise of cities, Reicher (2001) marks the French Third Republic as the 'birthplace of crowd psychology'. Reicher supports this claim with an example of the debate between Scipio Sighele and Gabriel Tarde in the 1890s. This debate concerned the struggle to distinguish between individual and crowd forces and how to determine criminal responsibility in a crowd. These concerns remain a problem that merits investigation to this day. The 1890s also saw Gustave Le Bon (1895) develop his theories of the crowd mind, observing that other forces must be at work as concentrated masses of people are more than just the sum of their component individuals. Therefore, the rising prevalence of crowds and opportunities to observe them have continued to spawn new lines of research and debate throughout the twentieth century and into the twenty-first. 165 Related to, and often part of, crowd research is the study and modelling of individual behaviour. The term 'individual' does not imply that such models isolate a person from others. Rather, individual behaviour models incorporate endogenous attitudes originating from within the person and account for the outside effects of physical and social influences. As a result, which forces are most important, their effects, and how they interact with each other have become a target of extensive study and many different models have been proposed. Among these proposed models are Fishbein and Ajzen's (1981) theory of reasoned action (TRA), and the many models that have been inspired by and descend from it. A variety of model compo...

show abstract

“…An usual approach to use the spatial scene information for distance evaluation algorithms is to transform the data given by the visual sensors into 3D point clouds (Bascetta et al, 2010;Pan et al, 2013). However, operating directly on the depth image provided by a depth sensor reduces the computation time (Flacco et al, , 2014.…”

Section: Distance Computation In the Depth Spacementioning

confidence: 99%

Human-aware motion reshaping using dynamical systems

Saveriano

Hirt

Lee

2017

Pattern Recognition Letters

View full text Add to dashboard Cite

In this work, we present a real-time approach for human-aware motion replanning using a two-level hierarchical architecture. The lower level leverages stable dynamical systems to generate motor commands and to online reshape the robot trajectories. The reshaping strategy modifies the velocity of the robot to match three requirements: i) to increase the human safety in case of close interaction with the robot, ii) to guarantee the correct task execution in case of unforeseen obstacles (including the human), and iii) to replan online the current task taking into account the human behavior. The lower level has to execute all needed computations in real-time. To this end, we also propose a novel approach that leverages depth space structure and parallel programming to rapidly and accurately estimate the robot-obstacle distances. The higher level of the architecture monitors the human and provides to the lower level information about the human status. The proposed approach has been tested in a human robot interaction scenario, showing promising results in terms of safe human-robot coexistence.

show abstract

Real-time collision detection and distance computation on point cloud sensor data

Cited by 30 publications

References 12 publications

Robust Contact Generation for Robot Simulation with Unstructured Meshes

Robust Contact Generation for Robot Simulation with Unstructured Meshes

Crowd dynamics of behavioural intention: train station and museum case studies

Human-aware motion reshaping using dynamical systems

Contact Info

Product

Resources

About