2013 The University of Queensland
Implementation of a walking pattern generator using Model-Predictive Control, for a full-sized humanoid robot.
(1 year, honors thesis)
2013 A*STAR Center for Infocomm Research
Testing real-time control software and repairing humanoid robots.
(4 weeks)
2013 PAL Robotics S.L.
Autonomous grasping of objects on table, using minimum-bounding boxes from object PointCloud data.
(2 months)
2012 Humanoid Robot Research Center “HUBO Lab” at KAIST
Developed Linux-based real-time control software, real-time CAN driver, motion planning for 6DOF manipulator, created simulation models of 6DOF manipulator and humanoid robot.
(11 months)
Robots and Language
This work was undertaken as part of a research placement with the “Lingodroids” group at the University of Queensland.

To enable robots to work collaboratively with humans, and operate safely around them, a robot needs to be able to
communicate effectively. However, have you ever given an instruction to a co-worker and found out later that they misunderstood you or that you used a phrase with a double meaning? Languages like English contain syntactic (structural) and lexical ambiguity [1] that will make it difficult for humans and robots to communicate effectively. Instead of trying to build robots that can communicate in a human-like way, we should be trying to develop a lexicon that allows humans to communicate with machines in a way that removes ambiguity [2] and so the operator has no doubt about what the robot will do next. It has been found that humans are more happy when they know the intentions of their robot coworker [3]; that is, what the robot will do when they encounter it in the workplace.

David T. Butterworth, “Robots and Language: A Practical Perspective” (un-published), 2010
Includes a literature review on symbol grounding and language development in robots.
PDF: Robots_and_Language_A_Practical_Perspective.pdf

[1] Here are some examples of ambiguity in the English language:
“The peasants are revolting” –
Some cases of ambiguity in English, for language students –

[2] There has been at least one attempt at developing a logical language:
John Woldemar Cowan, “The Complete Lojban Language”, The Logical Language Group, Inc., 1997

[3] The HV-100 robot from Harvest Automation uses a simple robotics technique to help with navigation whereby it follows a yellow line marked on the ground. The interesting thing is that this method was chosen not because it’s the only technology that works, but because it allows the human coworkers to quickly understand where the robot will move next.