Designing an Artificial Umwelt: Towards Natural Human-Robot Interaction

点击翻译按钮获取中文摘要

Phase one The aim within the first year of the project is to have developed a primitiveversion of the umwelt level, and begin tests using multi-modal data to explore thedevelopment of affordance-based observations. The system must be capable of recognising objects in its environment, and then recognising their affordances. Once object affordances are inferred correctly in the umwelt level, this makes the detection of communicative affordances - such as recognition of communicative intent through speech or gesture, or eye gaze - possible, opening up the ability to recognise other agents, as well as obtain channels for communicating with other agents in its environment. At this stage, the interaction the agent has with its objects around it will also ground its understanding in these interactions, creating grounded meaning.Phase two At this stage work can beginning on attaching the perceptuo-motor andumwelt layers together formally using the CNS level. Depending on the success of theumwelt to properly retrieve relevant information from the perceptuo-motors, a system ofpre-processing drivers may need to be implemented which transform the data into a formwhich the umwelt level is more capable of forming representations from.Phase three A mechanism for goal production then needs to be made, which will usethe affordances available in its environment to change its internal state. Observations ofits environment will be considered internally within the umwelt, so the system will beable to alter the state of its environment through trying to alter internal representationswhich correspond to this. This will to alter its environment through the formation andcompletion of goals will take place in the conscious level, and is intended to model consciousdecision-making.Phase four By this point the system would have a theory of mind. From here work canbe done on examining the effects of scaling the system. As the model is combined, theaffordances of the system will change depending on the modality of the agent. Work inthis area can examine the abilities of the agent to recognise goals in other agents, as wellas communicative gestures such as eye gaze.