Autonomous agents in a dynamic collaborative environment : a thesis presented in partial fulfilment of the requirements for the degree of PhD in Engineering at Massey University, Palmerston North, New Zealand
The proliferation of robots in industry and every day human life is gaining momentum.
After the initial few decades of employment of robots in the industry, especially the
automotive assembly plants, robots are now entering the home and offices. From being
pick-and-place manipulators, robots are slowly being transformed in shape and form to
be more anthropomorphic. The wheeled robots are however here to stay for the
foreseeable future until such time as artificial muscles, and efficient means to control
them, are well developed.
The next phase of development of robots will be for the service industry. Robots will
cooperate with each other to accomplish collaborative tasks to aid human life. They will
also collaborate with human beings to assist them in doing tasks such as lifting loads
and moving objects. At the same time, with the advancement of hardware, robots are
becoming very fast and are capable of being programmed with more intelligence.
Coupled with this is the availability of sophisticated sensors with which the robots can
perceive the real world around them. Combinations of these factors have created many
challenging areas of research.
Several factors affect the performance of robots in a dynamic collaborative
environment. The research presented in this thesis has identified the major contributing
factors, namely fast vision processing, behaviour programming, predictive movement
and interception control, and precise motion control, that collectively have influence
on the performance of robots which are engaged in a collaborative effort to accomplish
a task. Several novel techniques have been proposed in this thesis to enhance the
collective performance of collaborating robots.
In many systems, vision is used as one of the sensory inputs for the robot’s perception
of the environment. This thesis describes a new colour space and the use of discrete
look-up-tables (LUT) for very fast and robust colour segmentation and real-time
identification of objects in the robot’s work space. A distributed camera system and a
stereo vision using a single camera are reported. Advanced filtering has been applied to
the vision data for predictive identification of the position and orientation of moving
robots and targets, and for anticipatory interception control.
Collaborative tasks are generally complex and robots need to be capable of exhibiting
sophisticated behaviours. This thesis has detailed the use of State Transition Based
Control (STBC) methodology to build a hierarchy of complex behaviour. Behaviour of
robots in a robot soccer game and features such as role selection and obstacle avoidance
have been built using STBC.
A novel methodology for advanced control of fast robots is detailed. The algorithm uses
a combination of Triangular Targeting Algorithm (TTA) and Proximity Positioning
Algorithm (PPA) to position a robot behind an object aligned with a target. Various
forms of velocity profiling have been proposed and validated with substantial test
The thesis ends by looking at future scenarios where robots and human beings will
coexist and work together to do many collaborative tasks. Anthropomorphic robots will
be more prevalent in future and teleoperation will gain momentum.
Throughout the thesis, the engineering applicability of proposed algorithms and
architectures have been emphasised by testing on real robots.