c ar ma: towards personalized automotive tuning tobias flach 1, nilesh mishra 1, luis pedrosa 1,...
TRANSCRIPT
![Page 1: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/1.jpg)
CARMA: Towards Personalized Automotive Tuning
Tobias Flach1, Nilesh Mishra1, Luis Pedrosa1, Christopher Riesz2, Ramesh Govindan1
1 University of Southern California2 Rutgers University, Camden Campus
Sensys 2011
![Page 2: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/2.jpg)
2Motivation Architecture Evaluation ConclusionIntroduction
Introduction
Networked Sensing Smart Grid Smart Building
Smartphones Context awareness Participatory sensing
Automobiles On-board sensing Personalized tuning
Introduction
![Page 3: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/3.jpg)
3Motivation Architecture Evaluation ConclusionIntroduction
Sensing and Control in an Automobile
http://www.memsindustrygroup.org/files/public/April2010.htm
Introduction
Automobiles are highly customizable but this capability is not exposed to the user
![Page 4: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/4.jpg)
4Motivation Architecture Evaluation ConclusionIntroduction
Current Practice: Fixed Control Parameters
Driving behavior Terrain
Traffic Weather
Introduction
Factory defaults cannot cover all possible conditions
![Page 5: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/5.jpg)
5Motivation Architecture Evaluation ConclusionIntroduction
Our Goal: Flexible Personalized Tuning
Bob Alice
Introduction
CarMA can optimize for individual trips
![Page 6: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/6.jpg)
6Motivation Architecture Evaluation ConclusionIntroduction
Can Personalized Tuning Be Effective?
Impact of route characteristics?
Impact of driving behavior?
Interstate Route Hill Route Street route
Motivation
![Page 7: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/7.jpg)
7Motivation Architecture Evaluation ConclusionIntroduction
Can Personalized Tuning Be Effective?
Fuel economy for two cars on different routes (with different conditions)
Intrinsic variability
Extrinsic variability
Exploitable by personalized tuning
Motivation
![Page 8: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/8.jpg)
8Motivation Architecture Evaluation ConclusionIntroduction
Client device On-board diagnostics (OBD-II)
Engine control unit (ECU)
Background: Scanning and Tuning
Sensor Value
Intake manifold absolute pressure 32.0 kPa
RPM 1925 rev/min
Speed 16.0 km/h
Ignition timing advance 3.0 °(relative)
Throttle position 27.84 %
Injector pulse width 11.89 ms
Coolant Temperature
Transmission not engaged
Transmission engaged
-20°C 1200 1200
0°C 1106.05 964.65
20°C 1022.27 860.35
40°C 904.69 768.75
Table: Desired Idle RPM
Motivation
Scanning…Tuning…
![Page 9: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/9.jpg)
9Motivation Architecture Evaluation ConclusionIntroduction
Contributions: CarMA
Fosters ecosystem of car modifications
Wireless connectivity Programmability
Motivation
CARMA: A smartphone-based, make and model-independent platform providing programming abstractions for scanning and
tuning
On-Board Sensing
![Page 10: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/10.jpg)
10Motivation Architecture Evaluation ConclusionIntroduction
Contributions: Sample Apps
Improve responsiveness for hilly route
Maximize fuel efficiency
Support user diversity
Enforce safer driving behavior
Motivation
Implementation of sample apps that allow non-expert users to personalize and automatically optimize cars for different
drivers and/or route conditions
![Page 11: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/11.jpg)
11Motivation Architecture Evaluation ConclusionIntroduction
Contributions: Benefits of Personalized Tuning
A demonstration of personalized tuning that can exploit extrinsic variability to achieve significant
fuel efficiency or responsiveness gains
Motivation
![Page 12: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/12.jpg)
12Motivation Architecture Evaluation ConclusionIntroduction
CARMA Architecture
Architecture
![Page 13: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/13.jpg)
13Motivation Architecture Evaluation ConclusionIntroduction
Scanning Subsystem
Architecture
CARMA
1 2
3
4
5
6
Request: vehicle speed sensorRequest: 05 68 6A F1 01 0DResponse: 07 00 48 6B 10 41 0D 28Response: Vehicle Speed Sensor = 40 km/hVehicle Heterogeneity
Protocol Optimizations
Interface Heterogeneity
![Page 14: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/14.jpg)
14Motivation Architecture Evaluation ConclusionIntroduction
2
Tuning Subsystem
Architecture
CARMA
1
3
4
5
ECU memory
Download routine ECU firmwareOBD-II
interface
prepare();
setRPMLimit();commit();
Reverse Engineering Level of Abstraction
![Page 15: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/15.jpg)
15Motivation Architecture Evaluation ConclusionIntroduction
Mod Response Economy SafetyDisableEGR ✔ ✔
EnrichMixture ✔ ✔
IncreaseSparkTiming ✔ ✔
AdjustShiftDownPoints ✔ ✔ ✔
LimitRPM ✔ ✔ ✔
DecreaseShiftTime ✔
Tuning Subsystem: ModAPI
Client code CARMA code
tuner = ATuner.Stub.asInterface(service); tuner.loadCurrentSettings()tuner.applyMod(ModNames.LimitRPM, rpmVal)tuner.commitChanges()
new TableSetMod( ECUTableName.Disable_All_Injectors_High_MPH, 0, 0, 0, 2, 255),new TableSetMod( ECUTableName.Disable_All_Injectors_High_MPH, 1, 1, 0, 2, limit + 1),new TableSetMod( ECUTableName.Disable_1_Injector_High_MPH, limit),new TableSetMod( ECUTableName.Disable_2_Injectors_High_MPH, limit)
Architecture
tuner = ATuner.Stub.asInterface(service); tuner.loadCurrentSettings()tuner.applyMod(ModNames.LimitRPM, rpmVal)tuner.commitChanges()
new TableSetMod( ECUTableName.Disable_All_Injectors_High_MPH, 0, 0, 0, 2, 255),new TableSetMod( ECUTableName.Disable_All_Injectors_High_MPH, 1, 1, 0, 2, limit + 1),new TableSetMod( ECUTableName.Disable_1_Injector_High_MPH, limit),new TableSetMod( ECUTableName.Disable_2_Injectors_High_MPH, limit)
![Page 16: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/16.jpg)
16Motivation Architecture Evaluation ConclusionIntroduction
Evaluation Goals
Does CarMA raise the level of abstraction? Implementation of sample applications Micro-benchmarks
Does CarMA provide significant fuel efficiency gains? Test runs using route-specific fuel efficiency
optimizations on five different routes Comparison of the recorded sensor data from baseline
and modified runs
1
2
Evaluation
![Page 17: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/17.jpg)
17Motivation Architecture Evaluation ConclusionIntroduction
Evaluation: Applications
Scan App Tune Wizard Route Evaluator
Valet Mode Driver Customizer
98 LOC 214 LOC 408 LOC
60 LOC 76 LOC
Evaluation
![Page 18: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/18.jpg)
18Motivation Architecture Evaluation ConclusionIntroduction
Evaluation: Tune Wizard
Evaluation
Alice
Enable EGRIncrease torque timing
Limit RPM to 5000 Limit RPM to 3000
![Page 19: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/19.jpg)
19Motivation Architecture Evaluation ConclusionIntroduction
Sp eed
Elevati o n gain
Grad eC o n gesti o n
Traffic ligh ts
0
1
2
3
Sp eed
Elevati o n gain
Grad eC o n gesti o n
Traffic ligh ts
0
1
2
3
Sp eed
Elevati o n gain
Grad eC o n gesti o n
Traffic ligh ts
0
1
2
3
Evaluation: Fuel Efficiency Gains
Experimented with multiple drivers
Recorded data for more than 1100 miles
of driving
Recorded data for baseline runs and runs
using modifications
Evaluation
Speed limit
Elevationgain
Max. gradeCongestion
Traffic lights
![Page 20: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/20.jpg)
20Motivation Architecture Evaluation ConclusionIntroduction
Experimental Results: Fuel Economy
Fuel economy improved by
11% on average
Fuel economy for one driver
Evaluation
Would save more than
$18B in the US annually
Trip
![Page 21: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/21.jpg)
21Motivation Architecture Evaluation ConclusionIntroduction
Experimental Results: Validating Applications
RPM vs. throttle pos. for DriverCustomizer
Aggressive driving behavior
is prevented
Evaluation
![Page 22: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/22.jpg)
22Motivation Architecture Evaluation ConclusionIntroduction
Related Work
Evaluation
GreenGPS
Sensing
Control Analysis
MechanicsFirmwareUpgrade
Torque
Powr Tuner
eco:Drive
CARMA
![Page 23: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/23.jpg)
23Motivation Architecture Evaluation ConclusionIntroduction
Conclusions
CarMA provides programming abstractions for scanning and tuning automobiles via mobile devices
Usable by non-experts for personalized tuning
CarMA apps can achieve significant fuel efficiency gains by inhibiting aggressive driving behavior and enforcing limits
Conclusion
![Page 24: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/24.jpg)
24Motivation Architecture Evaluation ConclusionIntroduction
Future Work
Extending CarMA for a broader range of makes and models
Adding safety mechanisms to prevent accidental or malicious damage to vehicles using CarMA
Conclusion
![Page 25: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/25.jpg)
CARMA: Towards Personalized Automotive Tuning
Tobias Flach1, Nilesh Mishra1, Luis Pedrosa1, Christopher Riesz2, Ramesh Govindan1
1 University of Southern California2 Rutgers University, Camden Campus
Sensys 2011
![Page 26: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/26.jpg)
26Motivation Architecture Evaluation ConclusionIntroduction
Improving the State of the Art
Complexity
Expressivity
Fuel economy /
Performance modes
Specialized tuning
software
CARMA
![Page 27: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/27.jpg)
27Motivation Architecture Evaluation ConclusionIntroduction
Implemented functionality Checks for conflicting modifications Definition of safe value ranges for parameters
Additional ideas Application certification Mandatory "kill switch"
Security Considerations
Safe range
Value range (Desired Idle RPM; single cell)
0 25001200500 1700
![Page 28: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/28.jpg)
28Motivation Architecture Evaluation ConclusionIntroduction
Experimental Results: Economy variability
Impact of mods depends on “old” driving behavior
Fuel economy for different drivers
Evaluation
![Page 29: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/29.jpg)
29Motivation Architecture Evaluation ConclusionIntroduction
Experimental results: Speed and RPM limits
Speed limit is enforced RPM long tail is cut
Speed on trip 3 RPM CDF for trip 4B
![Page 30: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/30.jpg)
30Motivation Architecture Evaluation ConclusionIntroduction
Background: Scanning & Tuning
Motivation
![Page 31: C AR MA: Towards Personalized Automotive Tuning Tobias Flach 1, Nilesh Mishra 1, Luis Pedrosa 1, Christopher Riesz 2, Ramesh Govindan 1 1 University of](https://reader036.vdocuments.mx/reader036/viewer/2022070414/5697c0221a28abf838cd383f/html5/thumbnails/31.jpg)
31Motivation Architecture Evaluation ConclusionIntroduction
OBD-II Port