Analyzing the impact of learning inputs on near-to-far terrain traversability estimation

With the increasing need to adapt to new environments, data-driven approaches have been developed to estimate terrain traversability by learning the rover’s response on the terrain based on experience. Multiple learning inputs are often used to adequately describe the various aspects of terrain traversability. In a complex learning framework, it can be difficult to identify the relevance of each learning input to the resulting estimate. This paper addresses the suitability of each learning input by systematically analyzing the impact of each input on the estimate. Sensitivity Analysis (SA) methods provide a means to measure the contribution of each learning input to the estimate variability. Using a variance-based SA method, we characterize 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 propose an approach built on Analysis of Variance (ANOVA) decomposition to examine the prediction made in a near-to-far learning framework based on multi-task GP regression. We demonstrate the approach by analyzing the impact of driving speed and terrain geometry on the prediction of the rover’s attitude and chassis configuration in a Marsanalogue terrain using our prototype rover Mawson.

Nonparametric traversability estimation in partially occluded and deformable terrain

Terrain traversability estimation is a fundamental requirement to ensure the safety of autonomous planetary rovers and their ability to conduct long-term missions. This paper addresses two fundamental challenges for terrain traversability estimation techniques. First, representations of terrain data, which are typically built by the rover’s onboard exteroceptive sensors, are often incomplete due to occlusions and sensor limitations. Second, during terrain traversal, the rover-terrain interaction can cause terrain deformation, which may significantly alter the difficulty of traversal. We propose a novel approach built on Gaussian process (GP) regression to learn, and consequently to predict, the rover’s attitude and chassis configuration on unstructured terrain using terrain geometry information only. First, given incomplete terrain data, we make an initial prediction under the assumption that the terrain is rigid, using a learnt kernel function. Then, we refine this initial estimate to account for the effects of potential terrain deformation, using a near-to-far learning approach based on multitask GP regression. We present an extensive experimental validation of the proposed approach on terrain that is mostly rocky and whose geometry changes as a result of loads from rover traversals. This demonstrates the ability of the proposed approach to accurately predict the rover’s attitude and configuration in partially occluded and deformable terrain.

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.

The ghost in the city industrial complex: Le Corbusier and the fascist theory of Urbanisme

Le Corbusier participated in an urban dialogue with the first group in France to call itself fascist: the journalist Georges Valois’s militant Faisceau des Combattants et Producteurs (1925-1927), the “Blue Shirts,” inspired by the Italian “Fasci” of Mussolini. Le Corbusier’s portrait photograph materialised on the front cover of the January 1927 issue of the Faisceau League’s newspaper Le Nouveau Siècle edited by the former anarcho-syndicalist journalist Georges Valois, its leader, who fashioned himself as the French Mussolini. Le Corbusier was described in the Revue as one of les animateurs (the “organisers”) of the Party1 – meaning a member of the technical elite who would drive the Faisceau’s plans. On 1 May 1927, the Nouveau Siècle printed a full-page feature “Le Plan Voisin” on Le Corbusier’s 1922 redesign of Paris : the architect’s single-point perspective sketch appeared below an extract lifted from the architect’s original polemic Le Centre de Paris on the pages of Le Corbusier’s second book Urbanisme published two years earlier, a treatise on urbanism.2 Three weeks later, Le Corbusier presented a slide show of his urban plans at a fascist rally for the inauguration of the Faisceau’s new headquarters on the rue du faubourg Poissonniere, thereby crystalising the architect’s hallowed status in the league...