Analysing the Impact of Learning Inputs - Application to Terrain Traversability Estimation

Data-driven approaches such as Gaussian Process (GP) regression have been used extensively in recent robotics literature to achieve estimation by learning from experience. To ensure satisfactory performance, in most cases, multiple learning inputs are required. Intuitively, adding new inputs can often contribute to better estimation accuracy, however, it may come at the cost of a new sensor, larger training dataset and/or more complex learning, some- times for limited benefits. Therefore, it is crucial to have a systematic procedure to determine the actual impact each input has on the estimation performance. To address this issue, in this paper we propose to analyse the impact of each input on the estimate using a variance-based sensitivity analysis method. We propose an approach built on Analysis of Variance (ANOVA) decomposition, which can characterise how the prediction changes as one or more of the input changes, and also quantify the prediction uncertainty as attributed from each of the inputs in the framework of dependent inputs. We apply the proposed approach to a terrain-traversability estimation method we proposed in prior work, which is based on multi-task GP regression, and we validate this implementation experimentally using a rover on a Mars-analogue terrain.

Seeking continuity: Educational strategy in and for mobile ADF families

This report shares findings and insights from an interview study conducted in 2009, with 34 ADF families. These families were identified in the communities of primary schools in both state and Catholic systems with high ADF family enrolments in 3 towns across 2 states, with the assistance of the DCO and their embedded Defence School Transition Aides (DSTAs). In the interviews the parents were invited to describe their history of ADF relocations, and how they managed transitions for each member in terms of school choice, child care arrangements, spouse employment, and educational transitions. Parallel interviews were conducted with 12 teachers and 6 DSTAs across the identified schools to describe how schools cater for mobile ADF families flowing through their classes. Parents were invited to tell the story of their family’s sequence of moves and how each member made the transition, then reflect more generally on what advice they’d give other mobile families. Teachers were asked to describe how they respond to the mobile families in their school community, and to illustrate some of the issues and challenges from the institutional perspective. By offering perspectives from both parents and teachers, the report hopes to facilitate a dialogue between parties to address their common goal – promoting productive continuities in education for children in mobile families.

Place categorization and semantic mapping on a mobile robot

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot with-out environment-specific training. Motivated by their ongoing success in various visual recognition tasks, we build our system upon a state-of-the-art convolutional network. We overcome its closed-set limitations by complementing the network with a series of one-vs-all classifiers that can learn to recognize new semantic classes online. Prior domain knowledge is incorporated by embedding the classification system into a Bayesian filter framework that also ensures temporal coherence. We evaluate the classification accuracy of the system on a robot that maps a variety of places on our campus in real-time. We show how semantic information can boost robotic object detection performance and how the semantic map can be used to modulate the robot’s behaviour during navigation tasks. The system is made available to the community as a ROS module.