Interested in autonomous driving research? Participate in a relevant project. Learn more.
Prof Dr. Marco Hutter of the Robotic Systems Lab of ETH Zurich gave a talk on legged robotics and mobile manipulation on July 31st. The talk took place at the Knowledge Center, hosted and organized by the Autonomous Robots Lab.
Autonomous Aerial Robotic Exploration and Mapping of a Railroad Tunnel in Degraded Visual Conditions
This video presents indicative results of a sequence of field experiments conducted to verify and evaluate new algorithms and systems for autonomous exploration and mapping of tunnel environments using aerial robots. A multitude of such experiments were conducted to verify different algorithms and perception systems.
Tthe Tunnel 4 of V&T Railroad at Virginia City, Nevada was selected for these tests and refers to an approximately 14ft wide, 25ft tall and 450ft long old railway tunnel.
For its autonomous exploration, a small aerial robot equipped with a multi-modal localization and mapping unit, as well as localization uncertainty-aware exploration path planning intelligence was developed and utilized. Given no prior knowledge of its environment, the robot was deployed inside the tunnel and left to explore on its own. The result is a dense map of the tunnel revealing its geometrical and visual characteristics.
In addition, a set of further GPS-denied localization and mapping technologies were tested toward the very high-fidelity mapping of the tunnel from all possible perspectives.
Below the video from the Panel on "Democratization of Drones" at TiEcon 2017 moderated by Dr. Kostas Alexis
An Memorandum of Understanding between the University of Nevada, Reno and Queensland University of Technology was signed. The MOU establishes a collaborative relationship to facilitate research and the development of opportunities for new technologies, robotics and autonomous vehicles, air quality, exhaust emissions and hydrologic sciences.
On Friday 16 June, The autonomous vehicles bill AB 69 was signed. AB69 allows the use of fully autonomous vehicles for commercial use. The bill is considered key in helping Nevada play a key role in the development and use of autonomous vehicles. It will have important implications for the University's Intelligent Mobility initiative that our lab participates.
Below the coverage from KTVN which also shows segments of previous demonstrations of our lab: http://www.ktvn.com/story/35699801/lawmakers-approve-most-of-sandovals-requests
The presentations of the ICUAS2017 Workshop entitled "Robots in the Wild" are provided below.
Presentations of the ICRA 2017 Workshop on Autonomous Structural Monitoring and Maintenance using Aerial Robots
The presentations of the ICRA 2017 Workshop on Autonomous Structural Monitoring and Maintenance using Aerial Robots are now available online at: http://www.aerial-monitoring-maintenance-workshop.com/agenda--presentations.html
Open source code: https://github.com/unr-arl/rhem_planner
Autonomous exploration and reliable mapping of unknown environments corresponds to a major challenge for mobile robotic systems. For many important application domains, such as industrial inspection or search and rescue, this task is further challenged from the fact that such operations often have to take place in GPS-denied environments and possibly visually-degraded conditions.
During this ICRA conference we presented our work on "Uncertainty-aware Receding Horizon Exploration and Mapping using Aerial Robots" which aims to reliably address this problem. In this work, we move away from deterministic approaches on autonomous exploration and we propose a localization uncertainty-aware autonomous receding horizon exploration and mapping planner verified using aerial robots. This planner follows a two-step optimization paradigm. At first, in an online computed random tree the algorithm finds a finite-horizon branch that optimizes the amount of space expected to be explored. The first viewpoint configuration of this branch is selected, but the path towards it is decided through a second planning step. Within that, a new tree is sampled, admissible branches arriving at the reference viewpoint are found and the robot belief about its state and the tracked landmarks of the environment is propagated. The branch that minimizes the expected localization uncertainty is selected, the corresponding path is executed by the robot and the whole process is iteratively repeated.
During the IEEE ICRA 2017 "Autonomous Structural Monitoring and Maintenance using Aerial Robots" workshop we will present a talk on "Towards Robotically Supported Decommissioning of Nuclear Sites". We accompany this talk with the following discussion paper:
F. Mascarich, T. Wilson, T. Dang, S. Khattak, C. Papachristos, K. Alexis, "Towards Robotically Supported Decommissioning of Nuclear Sites." arXiv preprint arXiv:1705.06401 (2017).