TACO developed a 3D sensing system with 3D foveation properties endowing service robots with a higher level of motion and affordance perception and interaction capabilities with respect to everyday objects and environments.
By 3D foveation we mean properties based on the process of acquiring 3D images with coarse level of details, applying fast object recognition techniques to identify areas of interest in the coarse 3D image and then concentrate the image acquisition on details of interest, allowing for higher resolution 3D sampling of these details. This new 3D foveation concept should allow robots to interact with everyday environments in a more natural and human-like manner, increasing the level of detail whenever needed for interaction between the robot and everyday objects and humans.
The project verified and tested the 3D sensing system in a robotic environment, exploring the capabilities of the system to allow the robot to navigate autonomously and interact with a diverse number of everyday objects.
The specific scientific and technological (S&T) objectives of the TACO project were:
1. development of a flexible, compact, robust 3D imaging device;
2. achievement of 3D measurements of increased spatial and temporal resolution in detected regions of interest;
3. benchmarking of the 3D sensing system on robots in an everyday environment test bed, with interaction with everyday objects.
TACO had the following market and outreach (M&O) objectives:
1. provide new technology to the European robotics industry;
2. making TACO knowledge visible within industry and the scientific community;
3. carry out proof-of-concept validation of the concept.
The achievement of the TACO scientific and technical objectives were measured against an initial set of verifiable indicators.
In order to achieve the objectives, TACO went through three main phases of work: Requirements & Design, Production and Implementation and Validation & Testing.
Project work was organized to allow for two iterations of system building. At the end of phase 1, the project delivered a first version of all technical deliveries, including a system prototype with possibly limited capabilities. This allowed the system review by both the consortium partners and IAB, providing input for adjusting system design for the project´s phase 2.
The final prototype for validation and testing was finished at month 39. TACO was further structured in six RTD work packages:
WP1 - Requirements, Specifications and Roadmap was the keystone for defining the detailed focus of the entire project. In this work package, the consortium consulted with relevant robotic partners to achieve a common specification for the camera, and detail the project roadmap ahead for the remaining work packages.
WP2 - Advanced 3D perception concept detailed technological realisation of the specification output from WP1, including specification of all hardware and software components necessary for the camera, and the interfaces between them. This included doing performance evaluation and concept studies of critical technologies and design decisions. The result of this was a detailed design document for WP3 and WP4.
WP3 - 3D sensing device built and assembled the actual camera hardware. This included the MOEMS device, the optical design, time-of-flight sensor plus driver electronics and low level control software.
WP4 - Toolbox for adaptive control delivered a software package that provided the cameras with real-time cognitive and adaptive imaging abilities.
WP5 - System verification and Testing benchmarked and tested the sensor by performing proof-of-concept studies in natural environments, comparison studies with existing sensors and testing that the sensor was performing correctly.
WP6 - Dissemination, Standardisation and Exploitation had dependencies to all other work packages and followed the project throughout its life cycle. It managed the dissemination, exploitation and standardisation of the TACO project results in a coordinated manner in order to enable a maximum impact on the emerging wireless society. It was used to inform the academic community of the scientific result of the project, and to present the project and its potential impact to the European robotic and sensor industry.
WP7 - Project management had dependencies to all other work packages and accompanied the project. It was responsible for the operational management and technical life of the TACO project.