Technical White Paper Intelligent Fleet Management INTRODUCTION Managing a fleet of vehicles is a challenging task, especially with rising fuel and maintenance costs, concerns about driver and passenger safety, and the need to deliver excellent customer service. Helping fleet operators address these areas, evolving technology, and the rise of connected vehicles provide new opportunities to improve fleet performance and customer satisfaction. Nowadays, operating a fleet encompasses the management of vehicles, routes, and workers using a variety of technologies, including vehicle tracking, telematics, and smart surveillance. Making this easier, advanced fleet management systems allow fuel economy, driver behavior, and other things to be closely monitored by gathering useful data, such as mileage, speed, braking style, and fuel consumption. This information, collected by the vehicle s onboard computer and analyzed with data analytics, can produce valuable insights for fleet companies. Fleet management systems also allow fleet operators to remotely track vehicles using realistic maps and views generated from Global Positioning System (GPS) data. This advanced technology increases fleet management effectiveness and efficiency by reducing workload and overall transportation and staff costs.
Table of Contents Introduction...1 Technologies...2 Intel Solution...2 Data management...3 Telematics...3 Location-Based Advertisement...4 Smart Surveillance...4 Mobile Application...4 Case Study...6 Future Plan and Conclusion...7 Figures Figure 1. Fleet Management System Architechure...3 Figure 2. Key Elements for Location-Based Advertisement...4 Figure 3. Key Elements for Smart Surveillance...5 Figure 4. Key Elements for Mobile App Support...5 Figure 5. Aggressive Driving Test Result...6 Figure 6. Fuel Inefficient Driving Test Results...6 Technologies Various evolving technologies are providing crucial information to fleet operators, for instance, on-board diagnostics version 2 (OBDII) support vehicle self-diagnostic and reporting capabilities, which collect real-time vehicle parameters used for monitoring and performance analysis (e.g., fuel consumption rate). ODBII systems utilize in-vehicle buses, such as the controller area network (CAN bus), to allow microcontrollers and devices to communicate with each other without a host computer. Accelerometers measuring vehicle acceleration allow fleet operators to monitor driving patterns, such as excessive speed and harsh cornering. Fleet operators can avoid vehicle theft with remote vehicle disabling systems (RVDS) that can stop engines from starting, and stop or slow down moving vehicles. These systems use GPS technology to let operators know precisely where vehicles are located, significantly increasing the chances of recovering a stolen vehicle. Geofencing technology can detect when a vehicle goes outside a desired area so that alerts can be sent to warn of possible suspicious activity. Likewise, some fleet management solutions send notifications based on a configurable set of rules (e.g., excessive speed, very low tire pressure). Given the powerful capabilities of RVDS, security technologies are needed to ensure fleet management systems cannot be accessed by unauthorized users. Intel Solution Helping systems integrators incorporate key technologies for public transportation, Intel developed a fleet management system proof of concept (PoC). It can be customized to easily fit into a wide variety of commercial vehicles, including taxis, school buses, and logistic freight vehicles. The architecture, shown in Figure 1, features an in-vehicle system based on the Intel Atom processor E3827 and supports data management, telematics, smart surveillance, location-based advertisement, and mobile applications, which are described in the following. 2
CLOUD-BASED FLEET MANAGEMENT SERVER (Back-end) Bus Operator Private Cloud Public Cloud HTML5 WEB/APP: Fleet management app wireless/wired HTML5 WEB/APP: Advertisement app Advertisement Buyer wireless/ wired 3G & WiFi GPS Waiting Passengers HTML5 WEB/APP: Bus tracking app Driver and Passengers On Board ANDROID*-BASED FLEET MANAGEMENT CLIENT (Front-end) Figure 1. Fleet Management System Architecture. Data management With the Intel PoC, fleet operators can move away from maintaining fleet data manually. The PoC manages the data associated with vehicles, terminals, stops, users, and driver schedules, allowing operations to run more efficiently. The solution also creates optimized routes and stops, and drivers can be assigned work shifts based on their available time. Telematics The Intel PoC collects real-time telematics data from sensors located inside the vehicle and sends it over an Internet connection to the cloud, where it can be distributed to stakeholders or further processed by the data analytics software. Fuel consumption estimation Fleet operators can calculate the fuel consumption rate for each vehicle using data collected by the Intel PoC. For each trip, the PoC sends the starting and ending fuel levels, and miles travelled via OBDII parameters to the cloud. Pothole Detection The Intel PoC can inform local authorities about the location and severity of potholes, thus eliminating the need to send employees to constantly inspect roads. Accelerometers sense vehicle motion changes; and in general, potholes produce greater movement in the Z axis direction (up and down) than in the X or Y direction. When measurements exceed a certain threshold, the PoC can send the authorities an alert about the detected pothole and its GPS location and relative size. Driver Behavior Monitoring Fleet operators can continuously monitor driver behavior, and for those driving recklessly, send them an alert via the Intel PoC. Accelerometer and GPS data sent over OBDII to the control center may be used to detect speeding, and harsh cornering and breaking. When necessary, the control center can send the driver a warning in the form of a pop-up text-to-voice notification. 3
GPS In-Bus Passagers (Front and Back Panel) LOCATION-BASED ADVERTISEMENT Advertiser Interface Account registration and identity authentication (DoS attack). Available advertisement air-time: [Date, route, start and end location, duration]. Up-loading media content to Intel Cloud IBA server. Kept record of previously purchased advertisement for 1-month. Payment is mocked-up in phase-1. Lead-time: 1-day. Based on GPS location to identify the upcoming station. Playback advertisement content (AV) on front and back panel. Supported format: H.264, WMV, MPEG-4 @ 1280x720 HD resolution. Receive advertisement control update is pushed from control station over WiFi to control box at main and satellite terminals. The playback of advertisement and media content is fixed by playlist sent from control station. Control Station Advertisement is auto-synchronized by pushing content to bus control box. Advertisement is indexed by [date, route, start and end location, duration, customer-id, content-id]. Past advertisement content is retained in server for 1-month, to ease repurchase. A playlist of advertisement and media content is generated at control station and pushed to control box, the playlist scheduling is based on: Start and end location Date Figure 2. Key Elements for Location-Based Advertisement. Location-Based Advertisement Operators of bus or taxi fleets can generate incremental revenue by using the Intel PoC to play location-based advertisements on passenger panels inside their vehicles. Shops and restaurants would be able to purchase air time for advertisements that are shown when the commercial vehicle is in the vicinity. Figure 2 shows elements of the solution, including location detection, advertisement playback, advertiser interface, and control station, for managing advertisement delivery. Smart Surveillance Drivers can view video streams of passengers inside their vehicle to make sure everyone is safe using a smart surveillance system based on the Intel PoC. The implementation example in Figure 3 shows a driver panel that displays video streams from front and rear cameras when the vehicle is going less than 30 km/h; otherwise, the display is dimmed to avoid distraction. These streams, as well as a third stream from a driver camera, are stored on a Solid-State Drive (SDD) and downloaded to a control station once the vehicle reaches its bay. The video can also be streamed to the control center in real time at one frame-per-second over a 3G network. Mobile Application Passengers can get regular updates on their journey by installing an app on their mobile devices that receives alerts from the Intel PoC. When passengers are waiting at a bus station, they can check-in to the app, which will let the bus driver know they are waiting to be picked up. Passengers get three alerts: 1) when the bus is at the prior stop, 2) when the bus reaches the passenger s stop, and 3) when it reaches the passenger s destination. Figure 4 shows an implementation using the PoC to send the bus GPS coordinates to the control station, which generates alerts that are sent to passenger mobile devices via the PoC. 4
Driver Camera SMART SURVEILLANCE Front Camera Back Camera SSD at Control Box 3x AV streams are H.264 encoded at digital camera front before passing to control box. AV streams are sliced into 1-minute granularity for each indexing [BusID, RouteID, CameraID, YYYY-MM-DD, hh:mm]. AV streams are synchronized with control station through WiFi when bus is at main and satellite stations. Life-span: 2-day. 1 fps still image streams are sent to control station if snap-shot is triggered over 3G network. Control Station AV streams are pushed by control box over WiFi to Intel Cloud-hosted database. Storage life-span is 1 month. Control station can playback AV streams based on index [BusID, RouteID, CameraID, YYYY-MM-DD, hh:mm] downloaded to Intel Cloud. Snapshot trigger Control station can trigger 1 fps still-image streams over 3G. Driver Panel If bus speed <30 km/h, driver panel shows live-streaming of front and back camera content (video only), else driver panel is dimmed to avoid distratction. Figure 3. Key Elements for Smart Surveillance. ON-DUTY BUS TRACKING Driver Panel! GPS CAN Be notified of the next stop pre-check-in passengers amount and service rating. Passengers (Smart Devices) Bus route search (origin, destination, time) sorted from most recent to later. Pre-check-in service to track BoI (Bus of Intrest) and get three notifications. First notification: when the bus is at a stop ahead. Second notification: when the bus reaches the stop. Last notification: when the bus reaches the destination. Post-ride feedback: satisfaction level and comment. Control Station On-duty bus fleet health indication on coverage map based on GPS @ 30s intervals: Green: moving, on-time per route Orange: stop/idle (<1 minute) Blinking Orange: stop/idle (>1 minute) Controller can analyze individual bus info (driver profile, in-bus surveillance) In-bus 1 fps snapshot from cameras over 3G network Bus fleet passenger satisfaction charts: driver ranking and KPI. Black-Box-Servce (BBS): driving behavior and road-condition profiling. Figure 4. Key Elements for Mobile App Support. 5
Case Study Aggressive Driving Intel conducted case studies to measure the effectiveness of its fleet management system PoC. Company employees participated in a test to determine their driving behavior and how much it could be improved by the Intel PoC-based solution. In particular, aggressive driving and fuel-inefficient driving were taken into consideration in this test case. The participants were also asked their opinion about the study, and the responses were: They were not aware of their bad driving behavior before the test The solution helped to improve their driving OCCURENCE/100 MILES 120 100 80 60 40 20 0 KEY BEFORE AFTER ACCELERATION 5.885815185 BRAKING TURNING 2.788017719 110.9011493 Figure 5 shows driving behavior before and after the fleet management system was deployed. The occurrences of aggressive acceleration, braking, and turning were reduced by 57 percent, 30 percent, and 17 percent, respectively. 1 Most of the drivers tended to turn harshly, not realizing their unsafe practice; however, the Intel solution helped them recognize this driving pattern and correct it. During the test, the amount of time the participants drove at higher speeds (55 to 75 km/h) was monitored. Figure 6 shows the drivers drove for longer periods at faster speeds before the Intel solution was turned on. Afterwards, the drivers slowed down, which improved fuel economy. Therefore, fuel consumption rate decreased when the drivers were using the Intel solution. In conclusion, the Intel solution can improve driving behavior as well as reduce fuel consumption. 2.505986523 1.949100629 Figure 5. Aggressive Driving Test Result. 1 91.60772958 Fuel Inefficient Driving DURATION IN PERCENTAGE 1.8000% 1.6000% 1.4000% 1.2000% 1.0000% 0.8000% 0.6000% 0.4000% 0.2000% KEY BEFORE AFTER 55 60 65 70 75 80 85 90 1.6874% 1.3056% 0.6212% 0.1574% 0.0151% 1.5992% 0.6736% 0.3162% 0.0111% SPEED RANGE Figure 6. Fuel Inefficient Driving Test Results. 1 6
Future Plan and Conclusion The Intel Intelligent Fleet Management proof of concept (PoC) was developed to help accelerate innovation in fleet management. The immediate future plan is to align the solution with the Intel IoT Platform, an end-to-end reference model designed to unify and simplify connectivity and security for the Internet of Things (IoT). As a result, fleet operators and systems integrators can take advantage of this repeatable foundation that enables devices to deliver trusted data to the cloud. The solution will unify the gateway, connectivity, and security components in IoT deployments for fleet vehicles. Intel is also adding cloud analytics support for the Intel IoT Gateway so data collected from vehicles can be used to generate useful insights and value for fleet operators and consumers. With connectivity, security, scalability, and interoperability being addressed by the Intel PoC, it is expected that system integrators will be able to focus their efforts on customization and application development for mass deployment. For more information about Intel solutions for IoT, visit www.intel.com/iot The next revision of the Intel Intelligent Fleet Management PoC will include Mashery* API management and service creation framework, edge-to-cloud connectivity, and the ability to scale to different Intel architecture processors. This Intel Atom processor-based solution will be tested on the Wind River* Edge Management System, which is a pre-integrated, cloud-based middleware that enables customers to quickly build a solution and reduce time to market. The Enhanced Security for the Intel IoT Gateway will add advanced security management for the device. 7
1 Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. By using this document, in addition to any agreements you have with Intel, you accept the terms set forth below. You may not use or facilitate the use of this document in connection with any infringement or other legal analysis concerning Intel products described herein. You agree to grant Intel a non-exclusive, royalty-free license to any patent claim thereafter drafted which includes subject matter disclosed herein. INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHER- WISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. Intel may make changes to specifications and product descriptions at any time, without notice. Designers must not rely on the absence or characteristics of any features or instructions marked reserved or undefined. Do not finalize a design with this information. The products described in this document may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request. Contact your local Intel sales office or your distributor to obtain the latest specifications and before placing your product order. Copies of documents which have an order number and are referenced in this document, or other Intel literature, may be obtained by calling 1-800-548-4725, or go to: http://www.intel.com/design/literature.htm. 2015 Intel Corporation. All rights reserved. Intel, the Intel logo, and Intel Atom are trademarks of Intel Corporation in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. 0115/MW/HBD/PDF 331860-001US