Projects - User contributions [en]

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:49:33Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:1.png]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:2.png]]

[[File:8.png]]

Importance Density Funtion:

[[File:9.png]]

[[File:10.png]]

[[File:11.png]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3.png]]

4. Data fusion

[[File:4.png]]

== Map Building Algorithm ==

[[File:5.png]]

== Results ==

[[File:6.png]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7.png]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

== '''Team''' ==

== Group Members ==

Zhihao Xu

Zhi Qiao

== Supervisors ==

Said Al-Sarawi

Damith Ranasinghe

Brad Alexander

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:48:16Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:1.png]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:2.png]]

[[File:8.png]]

Importance Density Funtion:

[[File:9.png]]

[[File:10.png]]

[[File:11.png]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3.png]]

4. Data fusion

[[File:4.png]]

== Map Building Algorithm ==

[[File:5.png]]

== Results ==

[[File:6.png]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7.png]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

== '''Team''' ==

== Group Members ==

Zhihao Xu
Zhi Qiao

== Supervisors ==

Said Al-Sarawi
Damith Ranasinghe
Brad Alexander

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

File:11.png

2014-10-29T05:45:01Z

A1618915:

File:10.png

2014-10-29T05:44:50Z

A1618915:

File:9.png

2014-10-29T05:44:40Z

A1618915:

File:8.png

2014-10-29T05:44:25Z

A1618915:

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:44:09Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:1.png]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:2.png]]

[[File:8.png]]

Importance Density Funtion:

[[File:9.png]]

[[File:10.png]]

[[File:11.png]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3.png]]

4. Data fusion

[[File:4.png]]

== Map Building Algorithm ==

[[File:5.png]]

== Results ==

[[File:6.png]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7.png]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:40:54Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:1.png]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:2.png]]

𝜔_𝑘^𝑖∝𝜔_(𝑘−1)^𝑖 ├ 𝑝(𝑧_𝑘 |𝑥_𝑘^𝑖)𝑝(𝑥_𝑘^𝑖 |𝑥_(𝑘−1)^𝑖 )/├ 𝑞(𝑥_𝑘^𝑖 |𝑥_(𝑘−1)^𝑖,𝑧_𝑘 )

Importance Density Funtion:

[[File:2]]

[[File:3]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3.png]]

4. Data fusion

[[File:4.png]]

== Map Building Algorithm ==

[[File:5.png]]

== Results ==

[[File:6.png]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7.png]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:40:06Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:1.png]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:2.png]]

[[File:1]]

Importance Density Funtion:

[[File:2]]

[[File:3]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3.png]]

4. Data fusion

[[File:4.png]]

== Map Building Algorithm ==

[[File:5.png]]

== Results ==

[[File:6.png]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7.png]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

File:7.png

2014-10-29T05:38:01Z

A1618915:

File:6.png

2014-10-29T05:37:50Z

A1618915:

File:5.png

2014-10-29T05:37:39Z

A1618915:

File:4.png

2014-10-29T05:37:26Z

A1618915:

File:3.png

2014-10-29T05:37:16Z

A1618915:

File:2.png

2014-10-29T05:37:06Z

A1618915:

File:1.png

2014-10-29T05:36:56Z

A1618915:

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:34:16Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:Laser1]]

2. Particle Filter

1. Unweight value
2. Particles: Each reading weight
3. weight = posterior
4. Importance weight value
5. comparing with threshold
6. Re-sampling

[[File:particle]]

[[File:1]]

Importance Density Funtion:

[[File:2]]

[[File:3]]

3. RFID

Matching:
1. Prediction x2,y2,θ
2. Hypothesis test
3. If not same tag
4. re-sampling

Measurement:
1.ranking
2.log –normal Shadowing model P=P0+10*N*log(d/do)-ξP0,d0 reference N pass loss index ξ normal random variable (flat fading)

[[File:3]]

4. Data fusion

[[File:4]]

== Map Building Algorithm ==

[[File:5]]

== Results ==

[[File:6]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:33:24Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:Laser1]]

2. Particle Filter

1. Unweight value
�2. Particles: Each reading weight
3. weight = posterior 4. Importance weight value
5. comparing with threshold�
6. Re-sampling

[[File:particle]]

[[File:1]]

Importance Density Funtion:

[[File:2]]

[[File:3]]

3. RFID

Matching:
�1. Prediction x2,y2,θ
�2. Hypothesis test�
3. If not same tag
�4. re-sampling

Measurement:
�1.ranking
�2.log –normal Shadowing model �P=P0+10*N*log(d/do)-ξ�P0,d0 reference�N pass loss index�ξ normal random variable�(flat fading)

[[File:3]]

4. Data fusion

[[File:4]]

== Map Building Algorithm ==

[[File:5]]

== Results ==

[[File:6]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.

[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.

[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.

[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.

[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:32:56Z

A1618915:

== '''Project Information''' ==

== Project introduction ==

The project aims at adding RFID information (sematic information) to improve Robot localization and map building. In order to improve Robot localization and map building by using cheap equipment, objectives blow should be achieved:

1. Adding RFID information to improve Robot localization:

2. Using RFID information (sematic information) to improve Robot map building:
As the robot received the fused data the map has already waiting for update, but the robot does not know which groups of tags are describe one object, therefore, the robot need to base on the information that is described by RFID tag to group them. After group, the robot can use the tags’ information to update the map. Once the map is updated, robot can according to the sematic information to navigation.

== Project overview ==

[[File:System_overview.png]]

== Sensor Module Algorithm ==

1. Laser

Laser could not create an accurate map when there is no enough points and a objects locates on the scanning path

[[File:Laser1]]

2. Particle Filter

1. Unweight value
�2. Particles: Each reading weight
3. weight = posterior 4. Importance weight value
5. comparing with threshold�
6. Re-sampling

[[File:particle]]

[[File:1]]

Importance Density Funtion:

[[File:2]]

[[File:3]]

3. RFID

Matching:
�1. Prediction x2,y2,θ
�2. Hypothesis test�
3. If not same tag
�4. re-sampling

Measurement:
�1.ranking
�2.log –normal Shadowing model �P=P0+10*N*log(d/do)-ξ�P0,d0 reference�N pass loss index�ξ normal random variable�(flat fading)

[[File:3]]

4. Data fusion

[[File:4]]

== Map Building Algorithm ==

[[File:5]]

== Results ==

[[File:6]]

Test environment:
small room 10cm error: 0.0-0.7cm
pass loss index: 3.4 20cm error: 0.3-1.6cm
13 values 30cm error: 1.6-2.4cm
40cm error: 1.3-3.8cm

[[File:7]]

There are three rectangular objects in an environment by using four-tag algorithm. The purpose of this test is to verify the logic of the algorithm and the tag’s position in different condition (positive value and negative value). The left lower rectangular object is trying to simulate a normal object when the robot received accurate position. The right higher two graph are simulate two adjacent objects and the corner tags’ position the robot received are not accurate.

== Conclusion ==

In a short range
RFID error :3cm
laser error:5cm
total error: maximum 2.9cm.
human influence RFID sensor.
The robot is able to know which tags are describe the same object in the unknown environment
The robot have already obtained a sematic database to describe the environment.
works need to be done in the future:
1. Reducing human influences.
2. Cutting off twist action.
3. Long range RFID detection.
4. Real-Time mapping.
5. Tag define interface.
6. Link sematic database to Robot navigation package.

== Reference ==

[1]M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM: A factored solution to the simultaneous localization and mapping problem," in AAAI/IAAI, 2002, pp. 593-598.
[2]F. Dellaert, D. Bruemmer, and A. C. C. Workspace, "Semantic slam for collaborative cognitive workspaces," in AAAI Fall Symposium Series 2004: Workshop on The Interaction of Cognitive Science and Robotics: From Interfaces to Intelligence, 2004.
[3]D. Lymberopoulos, Q. Lindsey, and A. Savvides, "An empirical characterization of radio signal strength variability in 3-d ieee 802.15. 4 networks using monopole antennas," in Wireless Sensor Networks, ed: Springer, 2006, pp. 326-341.
[4]D. B. R. Dr S.Davey, Dr N.Gordon "Multi-sensor Data Fusion," in Multi-sensor Data Fusion, ed. The University of Adelaide: The University of Adelaide, 2013, pp. 37-40.
[5]A. Doucet, S. Godsill, and C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statistics and computing, vol. 10, pp. 197-208, 2000.

The aim of this project is to Improve robot SLAM with RFID, laser and odometers

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:22:41Z

A1618915:

File:System overview.png

2014-10-29T05:21:46Z

A1618915: A1618915 uploaded a new version of "File:System overview.png"

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:21:12Z

A1618915:

Projects:2014S1-39 Tell your Robot where to go with RFID (Improving Autonomous Navigation)

2014-10-29T05:20:30Z

A1618915: