How UGVs physically fail in the field

By Jennifer Carlson, Robin Roberson Murphy. IEEE Transactions on robotics, 2005

318 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a84c534c713c518567ad95ddc55081a2adbafc9f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Constraint-based planning and control for safe, semi-autonomous operation of vehicles (2012, background): “Remotely operating a ground vehicle under these conditions while monitoring the vehicle’s health status, the status of the mission/tasks, and the condition of the environment leads to high failure rates, with many of today’s UGV’s failing before having completed even one full shift [4].”
Understanding and Resolving Failures in Human-Robot Interaction: Literature Review and Model Development (2018, background): “Moreover, the (Carlson and Murphy, 2005) taxonomy doesn’t consider uncertainties in the interaction that result from varying environments and other agents.”
Black-box data-efficient policy search for robotics (2017, background): “Reinforcement Learning (RL) can help robots adapt to unforeseen situations, such as being damaged [1], [2], [3] or stranded [4].”
Symbiotic human-robot collaborative assembly (2019, background): “10 summarised the causes of potential accidents in HRC into three categories: (1) engineering failures, (2) human errors, and (3) poor environmental conditions [33,239].”
Reset-free Trial-and-Error Learning for Robot Damage Recovery (2016, background): “While these robots could certainly have been more robust and some falls prevented, even the best robots will encounter unforeseen situations: hardware failures will always be a possibility, especially with highly complex robots in complex environments [2].”
Robustness Testing of Autonomy Software (2017, background): “A historical analysis of robotic system failures indicates that while attention to hardware is warranted, software remains one of the major sources of error [5].”
Robots that can adapt like animals (2014, background): “3C, undam-aged: 24 [16; 41] seconds, 3 [2; 5] physical trials, repaired: 29 [16; 82] seconds, 3.5 [2; 10] trials).”
Human Performance Issues and User Interface Design for Teleoperated Robots (2007, background): “According to Carlson and Murphy [22], generally, reliability of the unmanned ground vehicle (UGV) performance in the field tends to be low (i.”