{"id":55,"date":"2019-01-19T05:58:36","date_gmt":"2019-01-19T05:58:36","guid":{"rendered":"http:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/?page_id=55"},"modified":"2020-04-11T18:49:43","modified_gmt":"2020-04-11T18:49:43","slug":"summary","status":"publish","type":"page","link":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/","title":{"rendered":"Collision Avoidance System"},"content":{"rendered":"

 <\/p>\n

Collision Avoidance System<\/h2>\n

According to the National Highway Safety Traffic Administration, 23% of the fatal crashes involving Class 8 Heavy Duty Trucks in the U.S. are opposite-direction crashes in the form of either head-on collisions or opposite-direction sideswipes. Such crashes most commonly occur on straight stretches of two-lane, two-way highways with speed limits between 45-65 mph. Crashes are typically caused by another vehicle encroaching on the lane of the truck. Delta Autonomy, in association with Daimler Trucks, is developing a Collision Avoidance System (CAS) to detect, analyze, and respond to such potential on-coming crashes.<\/p>\n

Collision Avoidance System is an\u00a0active safety system that:<\/p>\n

    \n
  1. Detects potential opposite-direction crashes with camera and RADAR sensors setup.<\/li>\n
  2. Generates a response mechanisms such as braking or evasive steering maneuvers to either mitigate or avoid a possible crash.<\/li>\n<\/ol>\n

    The proposed goals of the project are to:<\/p>\n

      \n
    1. Acquire camera and RADAR data using the existing sensors commissioned on Daimler class 8 heavy-duty trucks to develop our algorithms, with the help of a sensor rig.<\/li>\n
    2. Develop real-time software to detect on-coming vehicles, predict the possibility of head-on collision or sideswipe and plan evasive maneuvers including breaking and steering, with the help\u00a0of simulation models.<\/li>\n
    3. Demonstrate evasive maneuvers proof-of-concept utilizing scale model vehicles.<\/li>\n<\/ol>\n

       <\/p>\n

      Our Use Case<\/h3>\n

      \"\"<\/p>\n

      Joe is a 42-year-old truck driver who operates along the Portland-Idaho route on his Daimler\u00a0Western Star\u00ae 5700, a class 8 heavy-duty truck. It\u2019s 8 am in the morning and he has just begun his\u00a0journey from Portland to deliver construction equipment to Nampa, Idaho. The road is a two-lane\u00a0countryside highway. As a heavy duty truck driver, he loathes driving on two-lane highways. He\u00a0lost Jamie, a dear friend and fellow trucker in an accident on a two-lane highway. Sadly, Jamie\u2019s\u00a0case is not unique among the trucking community.\u00a0Joe knows that a couple of seconds delay in response could mean the difference between life\u00a0and death. He delivers freights averaging 66,000 pounds and with such heavy load, it is extremely\u00a0difficult to maneuver the truck as compared to a 4,000-pound car. Fortunately, the truck he drives\u00a0now comes with a Collision Avoidance System (CAS), developed by Delta Autonomy, a Pittsburgh\u00a0based start-up that aims at mitigating head-on collisions in class 8 heavy-duty trucks.\u00a0It\u2019s been two hours into the journey and Joe is cruising at 45 miles per hour on a two-lane\u00a0highway strip. It\u2019s a warm and sunny day and he notes a yellow bus coming on the opposite lane\u00a0completely oblivious to the fact that there is a red car just behind the bus, wanting to overtake the\u00a0bus.<\/p>\n

      Suddenly, the car departs it\u2019s lane and comes onto Joe\u2019s lane with the distance between them\u00a0lesser than a tenth of a mile. Joe had been focusing straight and suddenly he hears a crash alert. The\u00a0red car takes him by surprise. The long overhaul made him fatigued and the sudden appearance of\u00a0the car within 100 meters coming at him in the opposite direction startles him.\u00a0Fortunately, the Collision Avoidance System (CAS) takes control of the situation. All this while,\u00a0the system has been continuously watching out for vehicles on the opposite lane and predicting their\u00a0future trajectories. The CAS system took images from the on-board camera and fused it with the\u00a0RADAR information and computed the likelihood of collision in real time.<\/p>\n

      As soon as the red car departed its lane, the camera and RADAR picked up its presence and\u00a0started computing the possibility of collision. The system also was cognizant of ego-vehicle state\u00a0and was predicting ego-state a few seconds into the future. When the red car came into Joe\u2019s lane,\u00a0CAS immediately detected it and predicted that a crash is certain; thereby immediately warning Joe.\u00a0The system then starts planning various alternate trajectories for mitigating the crash in real\u00a0time. It comes to the conclusion that braking while turning sideways to the right would be the best\u00a0way to mitigate the crash and executes the maneuver. At the same time, CAS also starts alerting all\u00a0the other vehicles by honking. The red car driver, after being notified by the alert and seeing the\u00a0truck maneuvering, immediately starts slowing down to avoid the truck. Both the vehicles come\u00a0to a halt without colliding into one another. Joe restarts the vehicle and starts heading towards the\u00a0destination, all grateful to CAS and how it saved his and the lives of the passenger.<\/p>\n

      Delta Autonomy saves the day!<\/p>\n

       <\/p>\n

      <\/h3>\n

      Our Sponsors<\/span><\/h3>\n

      \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0<\/span>\"\"<\/a><\/p>\n

      \"\"<\/a>\"\"<\/p>\n","protected":false},"excerpt":{"rendered":"

        Collision Avoidance System According to the National Highway Safety Traffic Administration, 23% of the fatal crashes involving Class 8 Heavy Duty […]<\/p>\n","protected":false},"author":178,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-templates\/page_front-page.php","meta":{"footnotes":""},"class_list":["post-55","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/pages\/55","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/users\/178"}],"replies":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/comments?post=55"}],"version-history":[{"count":29,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/pages\/55\/revisions"}],"predecessor-version":[{"id":895,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/pages\/55\/revisions\/895"}],"wp:attachment":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2018teama\/wp-json\/wp\/v2\/media?parent=55"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}