Full Day Woskshop on
Software and Control
Architectures for Robotics
|
|
|
Invited
|
|
Objectives
Nowadays, effective robotic solutions targeting new application domains outside the classical industrial manufacturing processes, need to adapt to the unstructured and partially unknown environments where these systems are required to work. The above leads to an increase of complexity of the new generation of robotic platforms at the hardware, control and behavior layers. For such systems, the design and the implementation of a software and control architecture capable of dealing with the increased complexity of these platforms while permitting to implement a wide range of desired advanced capabilities combined with autonomy and adaptability, is crucial for enabling the effective usage of these robots in real-world scenarios.
From a software point of view, a robotic platform can be seen as a heterogeneous distributed system whose architecture needs to consider a set of design goals which are essential to execute complex tasks in the above described emerging applications, such as construction, factories of the future, robots in care, space and logistics.
These requirements can be shared among the different software layers (e.g. interoperability, flexibility, small footprint etc.) of the robots or specific to the single component: for example the Hardware Abstraction Layer (HAL) should provide Real-Time (RT) performances with minimum jitter at relatively high control frequency, while higher level software and control components, e.g. perception or planning modules, need to be deployed on multi-core parallel machines or on
cloud-based solutions in a transparent way for the user, assuring high computational power.
Understanding these challenges and finding a way to standardize the robot software and control architecture at the different layers, can be highly beneficial for the robotics research and industrial communities, since one of the main limitation of the employment of such systems outside the lab or the traditional industry cells, is the lack of a common software infrastructure that can ease the control of the robots, reuse the different components and eventually avoid tailor-made software.
From a software point of view, a robotic platform can be seen as a heterogeneous distributed system whose architecture needs to consider a set of design goals which are essential to execute complex tasks in the above described emerging applications, such as construction, factories of the future, robots in care, space and logistics.
These requirements can be shared among the different software layers (e.g. interoperability, flexibility, small footprint etc.) of the robots or specific to the single component: for example the Hardware Abstraction Layer (HAL) should provide Real-Time (RT) performances with minimum jitter at relatively high control frequency, while higher level software and control components, e.g. perception or planning modules, need to be deployed on multi-core parallel machines or on
cloud-based solutions in a transparent way for the user, assuring high computational power.
Understanding these challenges and finding a way to standardize the robot software and control architecture at the different layers, can be highly beneficial for the robotics research and industrial communities, since one of the main limitation of the employment of such systems outside the lab or the traditional industry cells, is the lack of a common software infrastructure that can ease the control of the robots, reuse the different components and eventually avoid tailor-made software.
Topics of Interest
1. Software architectures for robotics
2. Hardware modeling and abstraction
3. Cloud robotics
4. Software framework for motion control
5. Cognitive architectures for robotics
6. Deep learning architecture for computer vision
7. Software perception pipeline for robotics
8. Formal methods for analysis and design
9. Semantic computing
10. Parallel computing
11. Real-Time (RT) middleware infrastructures
2. Hardware modeling and abstraction
3. Cloud robotics
4. Software framework for motion control
5. Cognitive architectures for robotics
6. Deep learning architecture for computer vision
7. Software perception pipeline for robotics
8. Formal methods for analysis and design
9. Semantic computing
10. Parallel computing
11. Real-Time (RT) middleware infrastructures
