As urban environments manifest high levels of complexity it is of vital importance that safety systems embedded within autonomous vehicles (AVs) are able to accurately anticipate short-term future motion of nearby agents. This problem can be further understood as generating a sequence of coordinates describing the future motion of the tracked agent. Various proposed approaches demonstrate significant benefits of using a rasterised top-down image of the road, with a combination of Convolutional Neural Networks (CNNs), for extraction of relevant features that define the road structure (eg. driveable areas, lanes, walkways). In contrast, this paper explores use of Capsule Networks (CapsNets) in the context of learning a hierarchical representation of sparse semantic layers corresponding to small regions of the High-Definition (HD) map. Each region of the map is dismantled into separate geometrical layers that are extracted with respect to the agent’s current position. By using an architecture based on CapsNets the model is able to retain hierarchical relationships between detected features within images whilst also preventing loss of spatial data often caused by the pooling operation. We train and evaluate our model on publicly available dataset nuTonomy scenes and compare it to recently published methods. We show that our model achieves significant improvement over recently published works on deterministic prediction, whilst drastically reducing the overall size of the network.

Researchers and developers have suggested that the use of diegetic interfaces can enhance users' sense of presence and immersion in virtual reality (VR) applications. While concepts of diegetic interfaces in VR are analogous to those seen on 2D displays, little work has considered how they might integrate with the movement-based controllers commonly used in consumer VR systems, to create higher fidelity interactions. In this paper we present a study (N = 58) in which we compare participants' experiences of diegetic and non-diegetic tool management interfaces, in a prototype VR crime scene investigation (CSI) training application. Contrary to expectations, we do not find evidence that participants' sense of presence is elevated when using the diegetic interface; however, we suggest that this may be due to reported higher levels of perceived workload, which can act to degrade user experience and engagement. We conclude by discussing the relationship between diegetic interface design and interaction fidelity, and highlighting trade-offs between fidelity, engagement, and learning outcomes in VR training applications.

An important aspect of all robotic systems is sensing and there are many sensing modalities used including vision, tactile, olfactory and acoustics to name a few. This paper presents a robotic system for sensing in acoustics, specifically in elevation localization. The model presented is a two-stage model incorporating spectral analysis using artificial pinna and an artificial neural network for classification and elevation estimation. The spectral classifier uses notch filters to analyze changes in attenuation of certain frequencies with elevation. This paper shows how using the spectral output of a signal generated by an artificial pinna can be classified by a feed-forward backpropagation neural network to estimate the elevation of a sound-source.

In this paper we present a robotic head MIRA (multimodal interactive robot agent) which has been developed for studying the learning of human robot interaction and improving our understanding of human robot interaction techniques. In this paper we focus on two main aspects of the system; first, we describe how the robot head learns to recognise faces for supporting the interaction process between a human and MIRA. Second, we show how MIRA can learn to identify sound sources of interest and attend to the source location improving the social interaction effect. We propose that there is substantial potential for learning visual and auditory features in order to increase adaptability and robustness of robotic heads.

In this paper we describe a bioinspired hybrid architecture for acoustic sound source localisation and tracking to increase the signal to noise ratio (SNR) between speaker and background sources for a socially interactive robot's speech recogniser system. The model presented incorporates the use of interaural time difference for azimuth estimation and recurrent neural networks for trajectory prediction. The results are then presented showing the difference in the SNR of a localised and non-localised speaker source, in addition to presenting the recognition rates between a localised and non-localised speaker source. From the results presented in this paper it can be seen that by orientating towards the sound source of interest the recognition rates of that source can be increased

Recurrent neural networks (RNN) have been used in many applications for both pattern detection and prediction. This paper shows the use of RNN's as a speed classifier and predictor for a robotic sound source tracking system. The system requires extensive training to classify all possible speeds to enable dynamic tracking of the most prominent sound within the environment.

This paper describes an auditory robotic system capable of computing the angle of incidence of a sound source on the horizontal plane (azimuth). The system, with the use of an Elman type recurrent neural network (RNN), is able to dynamically track this sound source as it changes azimuthally within the environment. The RNN is used to enable fast tracking responses to the overall system over a set time, as opposed to waiting for the next sound position before moving. The system is first tested in a simulated environment and then these results are compared with testing on the robotic system. The results show that the development of a hybrid system incorporating cross-correlation and recurrent neural networks is an effective mechanism for the control of a robot that tracks sound sources azimuthally.