CAT-SLAM : probabilistic localisation and mapping using a continuous appearance-based trajectory

This paper describes a new system, dubbed Continuous Appearance-based Trajectory Simultaneous Localisation and Mapping (CAT-SLAM), which augments sequential appearance-based place recognition with local metric pose filtering to improve the frequency and reliability of appearance-based loop closure. As in other approaches to appearance-based mapping, loop closure is performed without calculating global feature geometry or performing 3D map construction. Loop-closure filtering uses a probabilistic distribution of possible loop closures along the robot’s previous trajectory, which is represented by a linked list of previously visited locations linked by odometric information. Sequential appearance-based place recognition and local metric pose filtering are evaluated simultaneously using a Rao–Blackwellised particle filter, which weights particles based on appearance matching over sequential frames and the similarity of robot motion along the trajectory. The particle filter explicitly models both the likelihood of revisiting previous locations and exploring new locations. A modified resampling scheme counters particle deprivation and allows loop-closure updates to be performed in constant time for a given environment. We compare the performance of CAT-SLAM with FAB-MAP (a state-of-the-art appearance-only SLAM algorithm) using multiple real-world datasets, demonstrating an increase in the number of correct loop closures detected by CAT-SLAM.

Towards brain-based sensor fusion for navigating robots

Current state of the art robot mapping and navigation systems produce impressive performance under a narrow range of robot platform, sensor and environmental conditions, in contrast to animals such as rats that produce “good enough” maps that enable them to function under an incredible range of situations. In this paper we present a rat-inspired featureless sensor-fusion system that assesses the usefulness of multiple sensor modalities based on their utility and coherence for place recognition during a navigation task, without knowledge as to the type of sensor. We demonstrate the system on a Pioneer robot in indoor and outdoor environments with abrupt lighting changes. Through dynamic weighting of the sensors, the system is able to perform correct place recognition and mapping where the static sensor weighting approach fails.

Vision-only autonomous navigation using topometric maps

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph --- as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

Towards persistent visual navigation using SMART

In this paper, we present SMART (Sequence Matching Across Route Traversals): a vision- based place recognition system that uses whole image matching techniques and odometry information to improve the precision-recall performance, latency and general applicability of the SeqSLAM algorithm. We evaluate the system’s performance on challenging day and night journeys over several kilometres at widely varying vehicle velocities from 0 to 60 km/h, compare performance to the current state-of- the-art SeqSLAM algorithm, and provide parameter studies that evaluate the effectiveness of each system component. Using 30-metre sequences, SMART achieves place recognition performance of 81% recall at 100% precision, outperforming SeqSLAM, and is robust to significant degradations in odometry.

Brain-inspired sensor fusion for navigating robots

Current state of the art robot mapping and navigation systems produce impressive performance under a narrow range of robot platform, sensor and environmental conditions, in contrast to animals such as rats that produce “good enough” maps that enable them to function under an incredible range of situations. In this paper we present a rat-inspired featureless sensor-fusion system that assesses the usefulness of multiple sensor modalities based on their utility and coherence for place recognition, without knowledge as to the type of sensor. We demonstrate the system on a Pioneer robot in indoor and outdoor environments with abrupt lighting changes. Through dynamic weighting of the sensors, the system is able to perform correct place recognition and mapping where the static sensor weighting approach fails.

Autonomous multisensor calibration and closed-loop fusion for SLAM

The vast majority of current robot mapping and navigation systems require specific well-characterized sensors that may require human-supervised calibration and are applicable only in one type of environment. Furthermore, if a sensor degrades in performance, either through damage to itself or changes in environmental conditions, the effect on the mapping system is usually catastrophic. In contrast, the natural world presents robust, reasonably well-characterized solutions to these problems. Using simple movement behaviors and neural learning mechanisms, rats calibrate their sensors for mapping and navigation in an incredibly diverse range of environments and then go on to adapt to sensor damage and changes in the environment over the course of their lifetimes. In this paper, we introduce similar movement-based autonomous calibration techniques that calibrate place recognition and self-motion processes as well as methods for online multisensor weighting and fusion. We present calibration and mapping results from multiple robot platforms and multisensory configurations in an office building, university campus, and forest. With moderate assumptions and almost no prior knowledge of the robot, sensor suite, or environment, the methods enable the bio-inspired RatSLAM system to generate topologically correct maps in the majority of experiments.

Vision-based simultaneous localization and mapping in changing outdoor environments

For robots operating in outdoor environments, a number of factors, including weather, time of day, rough terrain, high speeds, and hardware limitations, make performing vision-based simultaneous localization and mapping with current techniques infeasible due to factors such as image blur and/or underexposure, especially on smaller platforms and low-cost hardware. In this paper, we present novel visual place-recognition and odometry techniques that address the challenges posed by low lighting, perceptual change, and low-cost cameras. Our primary contribution is a novel two-step algorithm that combines fast low-resolution whole image matching with a higher-resolution patch-verification step, as well as image saliency methods that simultaneously improve performance and decrease computing time. The algorithms are demonstrated using consumer cameras mounted on a small vehicle in a mixed urban and vegetated environment and a car traversing highway and suburban streets, at different times of day and night and in various weather conditions. The algorithms achieve reliable mapping over the course of a day, both when incrementally incorporating new visual scenes from different times of day into an existing map, and when using a static map comprising visual scenes captured at only one point in time. Using the two-step place-recognition process, we demonstrate for the first time single-image, error-free place recognition at recall rates above 50% across a day-night dataset without prior training or utilization of image sequences. This place-recognition performance enables topologically correct mapping across day-night cycles.

Automated sensory data alignment for environmental and epidermal change monitoring

In this paper we present research adapting a state of the art condition-invariant robotic place recognition algorithm to the role of automated inter- and intra-image alignment of sensor observations of environmental and skin change over time. The approach involves inverting the typical criteria placed upon navigation algorithms in robotics; we exploit rather than attempt to fix the limited camera viewpoint invariance of such algorithms, showing that approximate viewpoint repetition is realistic in a wide range of environments and medical applications. We demonstrate the algorithms automatically aligning challenging visual data from a range of real-world applications: ecological monitoring of environmental change, aerial observation of natural disasters including flooding, tsunamis and bushfires and tracking wound recovery and sun damage over time and present a prototype active guidance system for enforcing viewpoint repetition. We hope to provide an interesting case study for how traditional research criteria in robotics can be inverted to provide useful outcomes in applied situations.

Superpixel-based appearance change prediction for long-term navigation across seasons

Changing environments pose a serious problem to current robotic systems aiming at long term operation under varying seasons or local weather conditions. This paper is built on our previous work where we propose to learn to predict the changes in an environment. Our key insight is that the occurring scene changes are in part systematic, repeatable and therefore predictable. The goal of our work is to support existing approaches to place recognition by learning how the visual appearance of an environment changes over time and by using this learned knowledge to predict its appearance under different environmental conditions. We describe the general idea of appearance change prediction (ACP) and investigate properties of our novel implementation based on vocabularies of superpixels (SP-ACP). Our previous work showed that the proposed approach significantly improves the performance of SeqSLAM and BRIEF-Gist for place recognition on a subset of the Nordland dataset under extremely different environmental conditions in summer and winter. This paper deepens the understanding of the proposed SP-ACP system and evaluates the influence of its parameters. We present the results of a large-scale experiment on the complete 10 h Nordland dataset and appearance change predictions between different combinations of seasons.

Contribuições para a localização e mapeamento em robótica através da identificação visual de lugares

Tese de doutoramento, Informática (Engenharia Informática), Universidade de Lisboa, Faculdade de Ciências, 2015

There is nothing that 'identifies me to that place' : Aboriginal Women's perceptions of health spaces and places

There is a growing body of literature within social and cultural geography that explores notions of place, space, culture, race and identity. The more recent works suggest that places are experienced and understood in multiple ways and are embedded within an array of politics. Memmott and Long, who have undertaken place-based research with Australian Indigenous people, present the theoretical position that ‘place is made and takes on meaning through an interaction process involving mutual accommodation between people and the environment’. They outline that places and their cultural meanings are generated through one or a combination of three types of people–environment interactions. These include: a place that is created by altering the physical characteristics of a piece of environment and which might encompass a feature or features which are natural or made; a place that is created totally through behaviour that is carried out within a specific area, therefore that specific behaviour becomes connected to that specific place; and a place created by people moving or being moved from one environment to another and establishing a new place where boundaries are created and activities carried out. All these ideas of places are challenged and confirmed by what Indigenous women have said about their particular use of, and relationship with, space within several health services in Rockhampton, Central Queensland. As my title suggests, Indigenous women do not see themselves as ‘neutral’ or ‘non-racialised’ citizens who enter and ‘use’ a supposedly neutral health service. Instead, Aboriginal women demonstrate they are active recognisers of places that would identify them within the particular health place. That is, they as Aboriginal women didn’t just ‘make’ place, the places and spaces ‘make’ them. The health services were identified as sites within which spatial relations could begin to grow with recognition of themselves as Aboriginal women in place, or instead create a sense of marginality in the failure of the spaces to identify them. The women’s voices within this paper are drawn from interviews undertaken with twenty Aboriginal women in Rockhampton, Central Queensland, Australia, who participated in a research project exploring ‘how the relationship between health services and Aboriginal women can be more empowering from the viewpoints of Aboriginal women’. The assumption underpinning this study was that empowering and re-empowering practices for Aboriginal women can lead to improved health outcomes. Throughout the interviews women shared some of their lived realities including some of their thoughts on identity, the body, employment in the health sector, service delivery and their notions of health service spaces and places. Their thoughts on health service spaces and places provide an understanding of the lived reality for Aboriginal women and are explored and incorporated within this paper.

Contrasting scenarios : embracing speech recognition

The purpose of this chapter is to describe the use of caricatured contrasting scenarios (Bødker, 2000) and how they can be used to consider potential designs for disruptive technologies. The disruptive technology in this case is Automatic Speech Recognition (ASR) software in workplace settings. The particular workplace is the Magistrates Court of the Australian Capital Territory.----- Caricatured contrasting scenarios are ideally suited to exploring how ASR might be implemented in a particular setting because they allow potential implementations to be “sketched” quickly and with little effort. This sketching of potential interactions and the emphasis of both positive and negative outcomes allows the benefits and pitfalls of design decisions to become apparent.----- A brief description of the Court is given, describing the reasons for choosing the Court for this case study. The work of the Court is framed as taking place in two modes: Front of house, where the courtroom itself is, and backstage, where documents are processed and the business of the court is recorded and encoded into various systems.----- Caricatured contrasting scenarios describing the introduction of ASR to the front of house are presented and then analysed. These scenarios show that the introduction of ASR to the court would be highly problematic.----- The final section describes how ASR could be re-imagined in order to make it useful for the court. A final scenario is presented that describes how this re-imagined ASR could be integrated into both the front of house and backstage of the court in a way that could strengthen both processes.

Face recognition across pose on video using eigen light-fields

We propose an approach to employ eigen light-fields for face recognition across pose on video. Faces of a subject are collected from video frames and combined based on the pose to obtain a set of probe light-fields. These probe data are then projected to the principal subspace of the eigen light-fields within which the classification takes place. We modify the original light-field projection and found that it is more robust in the proposed system. Evaluation on VidTIMIT dataset has demonstrated that the eigen light-fields method is able to take advantage of multiple observations contained in the video.

School Leadership, Literacy and Social Justice : The Place of Local School Curriculum Planning and Reform

School reform is a matter of both redistributive social justice and recognitive social justice. Following Fraser (Justice interruptus: critical reflections on the “postsocialist” condition. Routledge, New York, 1997), we begin from a philosophical and political commitment to the more equitable redistribution of knowledge, credentials, competence, and capacity to children of low socioeconomic, cultural, and linguistic minority and Indigenous communities whose access, achievement, and participation historically have “lagged” behind system norms and benchmarks set by middle class and dominant culture communities. At the same time, we argue that the recognition of these students and their communities’ lifeworlds, knowledges, and experiences in the curriculum, in classroom teaching, and learning is both a means and an end: a means toward improved achievement measured conventionally and a goal for reform and alteration of mainstream curriculum knowledge and what is made to count in the school as valued cultural knowledge and practice. The work that we report here was based on an ongoing 4-year project where a team of university teacher educators/researchers have partnered with school leadership and staff to build relationships within community. The purpose has been to study whether and how engagement with new digital arts and multimodal literacies could have effects on students “conventional” print literacy achievement and, secondly, to study whether and how the overall performance of a school could be generated through a focus on professional conversations and partnerships in curriculum and instruction – rather than the top-down implementation of a predetermined pedagogical scheme, package, or approach.

Literacy, place-based pedagogies and social justice

Our long-term program of research has considered the relationships between teachers’ work and identities, literacy pedagogies and schooling, particularly in high-poverty communities. Over the past decade, we have worked with teachers to consciously explore with them the possible productive synergies between critical literacy and place-based pedagogies, and the affordances of multimodal and digital literacies for students’ engagement with the places where they live and learn. These studies have been undertaken with teachers working and living in various locales—from the urban fringe to inner suburban areas undergoing urban renewal, to rural and regional communities where poverty and the politics of place bring certain distinctive opportunities and constraints to bear on pedagogy for social justice. There is now wider recognition that “social justice” may need rethinking to foreground the nonhuman world and the relation between people and politics of places, people, and environments in terms of “eco-social justice” (Green 2010; Gruenewald 2003b) or spatial justice (Soja 2011). In this chapter, we explore place as a site of knowing and as an object of study as developed through the Special Forever project by teachers in schools located in the Murray-Darling Basin bioregion. Putting the environment at the center of the literacy curriculum inevitably draws teachers into the politics of place and raises questions concerning what is worth preserving and what should be transformed. We consider how the politics of place both constrains and opens up possibilities for pedagogy for eco-social justice and review the pedagogical work that one teacher, Hannah, undertook with her upper primary class.