Hafiq’s paper on “Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots” was accepted to the 2nd Workshop on Social Robot Navigation: Advances and Evaluation (papers) held in conjunction with IEEE International Conference on Intelligent Robots and Systems 2023 (IROS 2023) on 5 October. We couldn’t travel to …
Hafiq’s Deep Reinforcement Learning-based robot is doing well in crowd navigation. The DRL model was trained in one crowd setting and tested in different unseen crowd settings. In simulation, we have tested with up to 12 moving obstacles at a speed close to the robot. In real-world, we have tested with 4 obstacles at a …
Hafiq’s DRL-based robot is doing well in crowd navigation Read More »
Amirul has implemented the Simultaneous Localization And Mapping (SLAM) on our Wanderer-v1 robot. The implementation was done from scratch involving writing Python scripts for the kinematics, motion and sensor models, particle filter for localization and A-star search for path planning. Details of the project is available here.
Hafiq has completed the implementation of the navigation ability for our Parallax Eddie mobile platform. The above video was recorded outside the Robolab V3 in the Integrated Science Building in the Universiti Brunei Darussalam (UBD). There wasn’t a long indoor corridor in the building that we could run the robot. Details of this project is …