Trajectory planning for robots in dynamic human environments

Svenstrup, Mikael; Bak, Thomas; Andersen, Hans Jørgen

doi:10.1109/iros.2010.5651531

Cited by 96 publications

(57 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, this work only studies sparse crowd interactions in scripted settings. Svenstrup et al (2010) combined rapidly exploring random trees (RRT) with a potential field based on proxemics. Pradhan et al (2011) took a similar proxemic potential function-based approach.…”

Section: Related Workmentioning

confidence: 99%

Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation

Trautman

Murray

et al. 2015

The International Journal of Robotics Research

231

170

View full text Add to dashboard Cite

We consider the problem of navigating a mobile robot through dense human crowds. We begin by exploring a fundamental impediment to classical motion planning algorithms called the ''freezing robot problem'': once the environment surpasses a certain level of dynamic complexity, the planner decides that all forward paths are unsafe, and the robot freezes in place (or performs unnecessary maneuvers) to avoid collisions. We argue that this problem can be avoided if the robot anticipates human cooperation, and accordingly we develop interacting Gaussian processes, a prediction density that captures cooperative collision avoidance, and a ''multiple goal'' extension that models the goal-driven nature of human decision making. We validate this model with an empirical study of robot navigation in dense human crowds (488 runs), specifically testing how cooperation models effect navigation performance. The multiple goal interacting Gaussian processes algorithm performs comparably with human teleoperators in crowd densities nearing 0.8 humans/m 2 , while a state-of-theart non-cooperative planner exhibits unsafe behavior more than three times as often as the multiple goal extension, and twice as often as the basic interacting Gaussian process approach. Furthermore, a reactive planner based on the widely used dynamic window approach proves insufficient for crowd densities above 0.55 people/m 2 . We also show that our noncooperative planner or our reactive planner capture the salient characteristics of nearly any dynamic navigation algorithm. Based on these experimental results and theoretical observations, we conclude that a cooperation model is critical for safe and efficient robot navigation in dense human crowds.

show abstract

Section: Related Workmentioning

confidence: 99%

Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation

Trautman

Murray

et al. 2015

The International Journal of Robotics Research

231

170

View full text Add to dashboard Cite

show abstract

“…The potential field represents persons moving in the area. For further information on the setup, see [16]. Fig.…”

Section: Methodsmentioning

confidence: 99%

Minimising computational complexity of the RRT algorithm a practical approach

Svenstrup

Bak

Andersen

2011

2011 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-Sampling based techniques for robot motion planning have become more widespread during the last decade. The algorithms however, still struggle with for example narrow passages in the configuration space and suffer from high number of necessary samples, especially in higher dimensions. A widely used method is Rapidly-exploring Random Trees (RRT's). One problem with this method is the nearest neighbour search time, which grows significantly when adding a large number of vertices. We propose an algorithm which decreases the computation time, such that more vertices can be added in the same amount of time to generate better trajectories. The algorithm is based on subdividing the configuration space into boxes, where only specific boxes needs to be searched to find the nearest neighbour. It is shown that the computational complexity is lowered from a theoretical point of view. The result is an algorithm that can provide better trajectories within a given time period, or alternatively compute trajectories faster. In simulation the algorithm is verified for a simple RRT implementation and in a more specific case where a robot has to plan a path through a human inhabited environment.

show abstract

“…The RRT algorithm is in Svenstrup et al (2010) modified in several ways to obtain an algorithm that works for planning a trajectory for the given problem. The overall mission of the robot is, to move forward through the environment with a desired average speed and direction, which can be set by a top level planner.…”

Section: Rrt Based Trajectory Planningmentioning

confidence: 99%

“…This will demonstrate the robustness of the algorithm over time. Specific parameters for the algorithm can be seen in Svenstrup et al (2010).…”

Section: Simulations In Crowded Environmentsmentioning

confidence: 99%