Towards Robust Affordance-Based Planning in Situational Graphs
conference paper
Behavior-Oriented Situational graphs can be used by autonomous robots to model their environment and to naturally model the behaviors that can be performed at a specific location. This is simple and effective if behavior execution is successful, but upon failure the situational graph needs to be updated in such a way that the robot can recover and replan its behaviors. In this work we present a framework which performs the graph update based on recognized affordances and domain knowledge, leading to more robust robots.
TNO Identifier
1006335
Source title
40th Anniversary of the IEEE International Conference on Robotics and Automation (ICRA@40)
Files
To receive the publication files, please send an e-mail request to TNO Repository.