Smart sensor - Revision history

Marcoo: Marcoo moved page Social robot assistant to Smart sensor: project concept changed

2018-02-01T15:15:07Z

Marcoo moved page Social robot assistant to Smart sensor: project concept changed

Marcoo at 13:46, 30 November 2017

2017-11-30T13:46:02Z

Marcoo at 16:23, 23 November 2017

2017-11-23T16:23:36Z

Marcoo at 16:11, 23 November 2017

2017-11-23T16:11:14Z

Marcoo at 16:10, 23 November 2017

2017-11-23T16:10:11Z

Marcoo: Created page with "{{StudentProjectTemplate |Summary=Social robot |Keywords=Social robot |TimeFrame=First half of 2018 |References=Scheeff M., Pinto J., Rahardja K., Snibbe S., Tow R. (2002) Exp..."

2017-09-27T12:44:04Z

Created page with "{{StudentProjectTemplate |Summary=Social robot |Keywords=Social robot |TimeFrame=First half of 2018 |References=Scheeff M., Pinto J., Rahardja K., Snibbe S., Tow R. (2002) Exp..."

New page

{{StudentProjectTemplate
|Summary=Social robot
|Keywords=Social robot
|TimeFrame=First half of 2018
|References=Scheeff M., Pinto J., Rahardja K., Snibbe S., Tow R. (2002) Experiences with Sparky, a Social Robot. In: Dautenhahn K., Bond A., Cañamero L., Edmonds B. (eds) Socially Intelligent Agents. Multiagent Systems, Artificial Societies, and Simulated Organizations, vol 3. Springer, Boston, MA
Cynthia Breazeal. 2003 Emotion and sociable humanoid robots.. International Journal of Human-Computer Studies 59(1-2):119-155
|Prerequisites=Robotics projects require much development/time
|Supervisor=Martin, maybe others
|Level=Master
|Status=Open
}}
This is a stub which will be filled out later.
-The general research area is social robotics, an applied area at the junction between robotics, pattern recognition, image processing, and human science.
Robots are increasingly being introduced into public and domestic settings to conduct various useful tasks for humans and alongside of humans.
For such technologies to perform effectively, it is crucial to ensure safety, trust, and acceptance.
Toward this, researchers are aiming to facilitate mutual recognition of actions and intentions between humans and the autonomous systems.
Recognition by robots can involve cameras, thermal cameras, and other kinds of sensors, and behavior generation is conducted to facilitate human recognition of robot actions and intentions.
The challenge is human behaviors and intentions are complex and difficult to model, recognize, and generate.
-Students will mostly develop software, not hardware. Students will use an existing robot (probably Baxter, which will also be shared with other students and researchers as needed.)
Expected results: a thesis, code, video, etc (it would also be nice, but not required, if the students would be willing to also write a six page shortened version of the thesis, to be submitted to a conference)

@@ Line 6: / Line 6: @@
 Robin R. Murphy. Dempster–Shafer Theory for Sensor Fusion in Autonomous Mobile Robots. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 14, NO. 2, APRIL 1998 197.
 |Prerequisites=Projects involving both software, hardware, and electronics require much development/time
-|Supervisor=Martin Cooney, (possibly Håkan Petterson)
+|Supervisor=Martin Cooney, Håkan Petterson
 |Author=Can Yang
 |Level=Master

@@ Line 12: / Line 12: @@
 }}
 Goal: small smart sensors
 Motivation:
 Current sensors are "static", detecting just one thing, such as light, sound, or touch, because of which in complex systems such as vehicles or homes many sensors are typically required.
@@ Line 17: / Line 18: @@
 Alternatively, an ensemble of dynamic sensors could acquire more information than the same number of static sensors.
 Furthermore, if such sensors can be made small, various benefits would emerge: e.g., making arbitrary surfaces embedded with sensors for robots such as intelligent skin, and interesting tasks at the micro scale could potentially be facilitated, such as monitoring cells inside of a person.
 Challenges:
 It is unknown how a sensor could be automatically changed into a different kind of sensor, a good strategy for changing a sensor or an ensemble of sensors, and how to achieve this at a small scale.
 Approach:
 The student will
 -Design transitions between some typical sensors
 -Design algorithms for calculating information/interestingness for each modality (possibly using change point detection) and for strategically allocating roles (like particles in a particle filter).
 -Design a strategy for the micro scale
 -Implement a macro-scale proof-of-concept, which can be switched manually or algorithmically, and a smaller proof-of-concept (mini, or micro; nano would be cool but would probably not be possible)
 -Evaluate
 -Thus, students will develop both software, and hardware/electronics
 Expected result: some ideas (new knowledge) of how to adapt different sensors, at different scales. Thesis, prototypes, video, hopefully a paper, possibly other such as code

@@ Line 5: / Line 5: @@
 |References=Surya G. Nurzaman, Utku Culha, Luzius Brodbeck, Liyu Wang, Fumiya Iida. (2013) Active Sensing System with In Situ Adjustable Sensor Morphology. PLoS ONE 8(12):e84090. doi:10.1371/journal.pone.0084090
 Robin R. Murphy. Dempster–Shafer Theory for Sensor Fusion in Autonomous Mobile Robots. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 14, NO. 2, APRIL 1998 197.
 |Prerequisites=Projects involving both software, hardware, and electronics require much development/time
-|Supervisor=Martin Cooney (possibly Håkan Petterson)
+|Supervisor=Martin Cooney, (possibly Håkan Petterson)
 |Level=Master
-|Status=Open
+|Status=Ongoing
 }}
 Goal: small smart sensors

← Older revision	Revision as of 15:15, 1 February 2018
(No difference)

@@ Line 1: / Line 1: @@
 {{StudentProjectTemplate
-|Summary=Social robot
+|Summary=Small smart sensors
-|Keywords=Social robot
+|Keywords=Smart sensors, adaptation, sensors
 |TimeFrame=First half of 2018
-|References=Scheeff M., Pinto J., Rahardja K., Snibbe S., Tow R. (2002) Experiences with Sparky, a Social Robot. In: Dautenhahn K., Bond A., Cañamero L., Edmonds B. (eds) Socially Intelligent Agents. Multiagent Systems, Artificial Societies, and Simulated Organizations, vol 3. Springer, Boston, MA
+|References=Surya G. Nurzaman, Utku Culha, Luzius Brodbeck, Liyu Wang, Fumiya Iida. (2013) Active Sensing System with In Situ Adjustable Sensor Morphology. PLoS ONE 8(12):e84090. doi:10.1371/journal.pone.0084090
-Cynthia Breazeal. 2003 Emotion and sociable humanoid robots.. International Journal of Human-Computer Studies 59(1-2):119-155
+Robin R. Murphy. Dempster–Shafer Theory for Sensor Fusion in Autonomous Mobile Robots. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 14, NO. 2, APRIL 1998 197.
-|Prerequisites=Robotics projects require much development/time
+|Prerequisites=Projects involving both software, hardware, and electronics require much development/time
-|Supervisor=Martin, maybe others
+|Supervisor=Martin Cooney (possibly Håkan Petterson)
 |Level=Master
 |Status=Open
 }}
-This is a stub which will be filled out later.
+Goal: small smart sensors
--The general research area is social robotics, an applied area at the junction between robotics, pattern recognition, image processing, and human science.
+Motivation:
-Robots are increasingly being introduced into public and domestic settings to conduct various useful tasks for humans and alongside of humans.
+Current sensors are "static", detecting just one thing, such as light, sound, or touch, because of which in complex systems such as vehicles or homes many sensors are typically required.
-For such technologies to perform effectively, it is crucial to ensure safety, trust, and acceptance.
+A "smart" sensor which could dynamically adapt itself (to detect different signals) could replace multiple static sensors, leading to less space taken, less cost, less work for installations, a greater ability to operate when changes occur, and possibly even easier repairs (self-healing).
-Toward this, researchers are aiming to facilitate mutual recognition of actions and intentions between humans and the autonomous systems.
+Alternatively, an ensemble of dynamic sensors could acquire more information than the same number of static sensors.
-Recognition by robots can involve cameras, thermal cameras, and other kinds of sensors, and behavior generation is conducted to facilitate human recognition of robot actions and intentions.
+Furthermore, if such sensors can be made small, various benefits would emerge: e.g., making arbitrary surfaces embedded with sensors for robots such as intelligent skin, and interesting tasks at the micro scale could potentially be facilitated, such as monitoring cells inside of a person.
-The challenge is human behaviors and intentions are complex and difficult to model, recognize, and generate.
+Challenges:
--Students will mostly develop software, not hardware. Students will use an existing robot (probably Baxter, which will also be shared with other students and researchers as needed.)
+It is unknown how a sensor could be automatically changed into a different kind of sensor, a good strategy for changing a sensor or an ensemble of sensors, and how to achieve this at a small scale.
-Expected results: a thesis, code, video, etc (it would also be nice, but not required, if the students would be willing to also write a six page shortened version of the thesis, to be submitted to a conference)
+Approach: