Human aware navigation of a mobile robot in crowded dynamic environments

Download
2019
Hacınecipoğlu, Akif
As mobile robots start operating in dynamic environments crowded with humans, human-aware and human-like navigation is required to make these robots navigate safely, efficiently and in socially compliant manner. People can navigate in an interactive and cooperative fashion so that, they are able to find their path to a destination even if there is no clear path leading to it. This is clearly a dexterity of humans. But the mobile robots which have to navigate in such environments lack this feature. Even perfect trajectory prediction of people is not sufficient if crowd density is above a certain level. Interactive and cooperative navigation ability of humans should be incorporated into navigation algorithms. Therefore, the scope of this study is to develop a navigation method that can be implemented in mobile robots which will make them able to navigate in crowded dynamic environments without freezing and/or frustration. For this purpose, pose-invariant and real-time people detection and tracking methods are developed initially. Then, an interactive and cooperative trajectory prediction algorithm is introduced. A mobile robot is regarded just as another agent, like other humans in the scene, so that, predicted trajectory for the robot itself becomes the planned path which results in human-like and human-aware navigation. All the developed components are tested and validated separately, and finally, together on a mobile robot. Results of the real world experiments showed that the developed method can effectively make a mobile robot navigate in human-aware fashion in dynamic environments crowded with humans.

Suggestions

Multiple human trajectory prediction and cooperative navigation modeling in crowded scenes
Hacinecipoglu, Akif; Konukseven, Erhan İlhan; Koku, Ahmet Buğra (Springer Science and Business Media LLC, 2020-07-01)
As mobile robots start operating in environments crowded with humans, human-aware navigation is required to make these robots navigate safely, efficiently and in socially compliant manner. People navigate in an interactive and cooperative fashion so that, they are able to find their path to a destination even if there is no clear route leading to it. There are significant efforts to solve this problem for mobile robots; however, they are not scalable to high human density and learning based approaches depen...
Sensor based planning: A control law for generating the generalized Voronoi graph
Choset, H; Konukseven, Erhan İlhan; Rizzi, A (1997-01-01)
We introduce a new control law for robots that explore unknown environments and configuration spaces. Unlike numerical continuation methods, which produce a jagged path because of the predictor-corrector approach, the control law, introduced in this paper, performs sensor based planning by directing the head of a robot to follow continuously a roadmap. Recall that a roadmap is a one-dimensional representation of a robot's environment. Once the robot exhaustively traces out the roadmap using this control law...
The learning and use of traversability affordance using range images on a mobile robot
Ugur, Emre; Dogar, Mehmet R.; Cakmak, Maya; Şahin, Erol (2007-04-14)
We are interested in how the concept of affordances can affect our view to autonomous robot control, and how the results obtained from autonomous robotics can be reflected back upon the discussion and studies on the concept of affordances. In this paper, we studied how a mobile robot, equipped with a 3D laser scanner, can learn to perceive the traversability affordance and use it to wander in a room filled with spheres, cylinders and boxes. The results showed that after learning, the robot can wander around...
Pose invariant people detection in point clouds for mobile robots
Hacinecipoglu, Akif; Konukseven, Erhan İlhan; Koku, Ahmet Buğra (2020-05-01)
To be able to navigate in socially complaint fashion and safely, people detection is a very important ability for robots deployed in our social environments. However, it is a challenging task since humans exhibit various poses in daily life as they bend, sit down, touch or interact with each other. A robust people detector should detect humans also in these arbitrary poses. In addition, mobile robots should be able to carry out detection in a real-time manner because our environment is highly dynamic. In th...
Slippage estimation of a two wheeled mobile robot using deep neural network
Özçil, İsmail; Konukseven, Erhan İlhan; Koku, Ahmet Buğra; Department of Mechanical Engineering (2018)
Mobile robot navigaiton is an important task for the operations of the mobile robots. Due to the wheel slippages, performance of the dead reckoning in estimating speed of the robot and the position of the robot is not sufficient. To overcome the errors in navigation estimates, usage of the recurrent deep neural networks is porposed. Neural networks are used to understand the behaviour of the linear and nonlinear systems. Since wheel-ground interaction will be modeled with non-linear models and the estimatin...
Citation Formats
A. Hacınecipoğlu, “Human aware navigation of a mobile robot in crowded dynamic environments,” Thesis (Ph.D.) -- Graduate School of Natural and Applied Sciences. Mechanical Engineering., Middle East Technical University, 2019.