Gautham P. Das

Steering a predator robot using a mixed frame/event-driven convolutional neural network

This paper describes the application of a Convolutional Neural Network (CNN) in the context of a predator/prey scenario. The CNN is trained and run on data from a Dynamic and Active Pixel Sensor (DAVIS) mounted on a Summit XL robot (the predator), which follows another one (the prey). The CNN is driven by both conventional image frames and dynamic vision sensor “frames” that consist of a constant number of DAVIS ON and OFF events. The network is thus “data driven” at a sample rate proportional to the scene activity, so the effective sample rate varies from 15 Hz to 240 Hz depending on the robot speeds. The network generates four outputs: steer right, left, center and non-visible. After off-line training on labeled data, the network is imported on the on-board Summit XL robot which runs jAER and receives steering directions in real time. Successful results on closed-loop trials, with accuracies up to 87% or 92% (depending on evaluation criteria) are reported. Although the proposed approach discards the precise DAVIS event timing, it offers the significant advantage of compatibility with conventional deep learning technology without giving up the advantage of data-driven computing.

A Distributed Task Allocation Algorithm for a Multi-Robot System in Healthcare Facilities

Various ambient assisted living (AAL) technologies have been proposed for improving the living conditions of elderly people. One of them is to introduce robots to reduce dependency on support staff. The tasks commonly encountered in a healthcare facility such as a care home for elderly people are heterogeneous and are of different priorities. A care home environment is also dynamic and new emergency priority tasks, which if not attended shortly may result in fatal situations, may randomly appear. Therefore, it is better to use a multi-robot system (MRS) consisting of heterogeneous robots than designing a single robot capable of doing all tasks. An efficient task allocation algorithm capable of handling the dynamic nature of the environment, the heterogeneity of robots and tasks, and the prioritisation of tasks is required to reap the benefits of introducing an MRS. This paper proposes Consensus Based Parallel Auction and Execution (CBPAE), a distributed algorithm for task allocation in a system of multiple heterogeneous autonomous robots deployed in a healthcare facility, based on auction and consensus principles. Unlike many of the existing market based task allocation algorithms, which use a time extended allocation of tasks before the actual execution is initialised, the proposed algorithm uses a parallel auction and execution framework, and is thus suitable for highly dynamic real world environments. The robots continuously resolve any conflicts in the bids on tasks using inter-robot communication and a consensus process in each robot before a task is assigned to a robot. We demonstrate the effectiveness of the CBPAE by comparing its simulation results with those of an existing market based distributed multi-robot task allocation algorithm and through experiments on real robots.

A fast distributed auction and consensus process using parallel task allocation and execution

In a multi-robot system, the coordination and cooperation among the robots determine the effectiveness of task execution. Different centralised and distributed task allocation algorithms have been proposed by researchers. Recently consensus based task allocation has been extensively researched because of its robustness in handling large teams of robots. We propose a new auction and consensus based algorithm for fast task allocation in parallel with task execution. The performance of the proposed algorithm under different conditions is analyzed and compared with other distributed consensus algorithms.

Modelling of a retinal ganglion cell with simple spiking models

Modelling aspects of the human vision system, including the retina, is difficult due to insufficient knowledge about the internal components, organisation and complexity of the interactions within the system. Retinal ganglion cells are considered a core component of the human visual system as they convey the accumulated data as action potentials onto the optic nerve. Current techniques capable of mapping this input-output response involve computational combinations of linear and nonlinear models that are generally complex and lack any relevance to the underlying biophysics. This paper aims to model a retinal ganglion cell with a simple spiking neuron combined with a pre-processing method, which accounts for the preceding retinal neural structure. Performance of the models is compared with the spike responses obtained in the electrophysiological recordings from a mammalian retina subjected to visual stimulation.

Combined frame- and event-based detection and tracking

This paper reports an object tracking algorithm for a moving platform using the dynamic and active-pixel vision sensor (DAVIS). It takes advantage of both the active pixel sensor (APS) frame and dynamic vision sensor (DVS) event outputs from the DAVIS. The tracking is performed in a three step-manner: regions of interest (ROIs) are generated by a cluster-based tracking using the DVS output, likely target locations are detected by using a convolutional neural network (CNN) on the APS output to classify the ROIs as foreground and background, and finally a particle filter infers the target location from the ROIs. Doing convolution only in the ROIs boosts the speed by a factor of 70 compared with full-frame convolutions for the 240×180 frame input from the DAVIS. The tracking accuracy on a predator and prey robot database reaches 90% with a cost of less than 20ms/frame in Matlab on a normal PC without using a GPU.

Simultaneous allocations of multiple tightly-coupled multi-robot tasks to coalitions of heterogeneous robots

Most multi-robot task allocation algorithms are concerned with the allocation of individual tasks to single robots. However certain types of tasks require a team of robots for their execution, and for the allocation of such tasks non-conflicting robot teams have to be formed. Most of the existing allocation algorithms for such tasks mainly address the robot-team formation and the tasks are allocated sequentially. However, allocating multiple tasks simultaneously will result in a more balanced distribution of robots into teams. A market based algorithm for simultaneous allocation of multiple tightly couple multi-robot tasks to coalitions of heterogeneous robots are proposed in this paper. The simultaneous allocations are deadlock-free and significant improvement in overall execution time is achieved as demonstrated by empirical evaluations.

Novelty detection in user behavioural models within ambient assisted living applications: An experimental evaluation

Current approaches to networked robot systems (or ecology of robots and sensors) in ambient assisted living applications (AAL) rely on pre-programmed models of the environment and do not evolve to address novel states of the environment. Envisaged as part of a robotic ecology in an AAL environment to provide different services based on the events and user activities, a Markov based approach to establishing a user behavioural model through the use of a cognitive memory module is presented in this paper. Upon detecting changes in the normal user behavioural pattern, the ecology tries to adapt its response to these changes in an intelligent manner. The approach is evaluated with physical robots and an experimental evaluation is presented in this paper. A major challenge associated with data storage in a sensor rich environment is the expanding memory requirements. In order to address this, a bio-inspired data retention strategy is also proposed. These contributions can enable a robotic ecology to adapt to evolving environmental states while efficiently managing the memory footprint.

Computational modelling of salamander retinal ganglion cells using machine learning approaches

Abstract Artificial vision using computational models that can mimic biological vision is an area of ongoing research. One of the main themes within this research is the study of the retina and in particular, retinal ganglion cells which are responsible for encoding the visual stimuli. A common approach to modelling the internal processes of retinal ganglion cells is the use of a linear – non-linear cascade model, which models the cell’s response using a linear filter followed by a static non-linearity. However, the resulting model is generally restrictive as it is often a poor estimator of the neuron’s response. In this paper we present an alternative to the linear – non-linear model by modelling retinal ganglion cells using a number of machine learning techniques which have a proven track record for learning complex non-linearities in many different domains. A comparison of the model predicted spike rate shows that the machine learning models perform better than the standard linear – non-linear approach in the case of temporal white noise stimuli.