Event-based signaling for reducing required data rates and processing power in a large-scale artificial robotic skin

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Cheng

2016

Self Cite

Abstract-In this paper we describe how we realized eventbased signaling for large scale artificial robotic skin. We developed a new algorithm for the event generation on multi-modal skin cells. The skin cells have two modes, the conventional data sampling mode and the event mode. A comprehensive performance evaluation and comparison of these two modes is presented. We perform different experiments on our robot TOMM which has two UR5 robot arms, each covered with 260 multi-modal skin cells. Each skin cell samples 9 signals of 4 different modalities. Finally we derive models for extrapolating CPU usage and network traffic for larger numbers of skin cells and higher sample rates. The results show that the eventbased system has superior performance and its performance edge increases with larger numbers of skin cells and higher sample rates. Experimental validation on our real robot system shows that in reactive control the event-based system reduces in comparison to the conventional system the packet rate by 48.2% and the CPU usage by 17.79%. We extrapolate the worst case for 5000 cells and show that the event-based system can at least reduce the packet rate by 21.2% and the CPU usage by 17.46%.

Section: A Motivationmentioning

confidence: 97%

Section: B Event Generationmentioning

confidence: 99%

See 1 more Smart Citation

Event-based signaling for large-scale artificial robotic skin - realization and performance evaluation

Bergner

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Cheng

2016

Self Cite

“…For each control update it is necessary to browse active cells in each patch and to sum-up their corresponding force contributions as exposed in the algorithms 1 and 2. While the amount of generated data is substantial, it is nevertheless handled very efficiently [20], thereby guaranteeing extremely low latency. TOMM's central unit is based on two intel i7 computers with 16 Gb of RAM each: the first unit is dedicated to control tasks while the second one is used for machine learning and vision.…”

Section: A Implementation Details and Hardwarementioning

confidence: 99%

Tactile-based compliance with hierarchical force propagation for omnidirectional mobile manipulators

Leboutet

2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)

Cheng

2016

Self Cite

Abstract-In this paper, we address the issue of wholebody compliance with hierarchical force propagation for omnidirectional mobile manipulators. Using the multimodal tactile feedback (force and proximity) provided by an artificial skin, our objective is to generate prioritized compliant behaviors in response to multicontact physical interactions between a mobile robot and its external environment. To be more specific the force components which cannot be properly propagated using upper-limbs must be projected onto the mobile base in order to generate suitable compliant motions. Using Quadratic Programming (QP), we propose a general method allowing to properly estimate and propagate these force components while respecting the robot physical constraints. In this way, robust whole-body compliance can be achieved. We finally test and validate our method on a complex robotic system.

“…With 300 skin cells this processing load impacts the performance of real time control and this is more evident when the number of skin cells increases. In order to cope with this problem we use eventbased signaling [23]. We take advantage of the distributed micro-controllers of the skin cells and generate events on site.…”

Section: A Event-based Signalingmentioning

confidence: 99%

Robotic technologies for fast deployment of industrial robot systems

IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society

Ramirez-Amaro

Bergner

et al. 2016

Self Cite

Abstract-The development of breakthrough technologies helps the deployment of robotic systems in the industry. The implementation and integration of such technologies will improve productivity, flexibility and competitiveness, in diverse industrial settings specially for small and medium enterprises. In this paper we present a framework that integrates three novel technologies, namely safe robot arms with multi-modal and auto-calibrated sensing skin, a robot control framework to generate dynamic behaviors fusing multiple sensor signals, and an intuitive and fast teaching by demonstration method that segments and recognizes the robot activities on-line based on re-usable semantic descriptions. In order to validate our framework, these technologies are integrated in a industrial setting to sort and pack fruits. We demonstrate that our presented framework enables a standard industrial robotic system to be flexible, modular and adaptable to different production requirements.