internetofvehicle-Bennet.pdf
- 1. Presented by M.S.Bennet Praba,AP/CSE, SRMIST M.S. Bennet Praba,AP/CSE,SRMIST
- 2. Introduction Objective Existing Problem Proposed System Architectural Diagram References M.S. Bennet Praba,AP/CSE,SRMIST
- 3. Internet of Vehicles(IoV) is an extended application of IoT in intelligent transportation. It is envisioned to serve as an essential data sensing and processing platform for intelligent transportation systems. A vehicle will be a sensor platform, absorbing information from the environment, from other vehicles, from the driver and using it for safe navigation, pollution control, and traffic management. M.S. Bennet Praba,AP/CSE,SRMIST
- 4. Propose a framework by using efficient deep learning technique for avoiding rear end collision in IoV M.S. Bennet Praba,AP/CSE,SRMIST
- 5. Existing Collision Avoidance System (CAS) Not fast Not accurate enough to take initial action in CAS. If more robust and accurate the products are, the higher price/cost may be. M.S. Bennet Praba,AP/CSE,SRMIST
- 6. Ref Issue Identified Method /Approach / Algorithm used R1 Accuracy is less Real-Time Collision Detection using Neural Networks –A multilayer perception algorithm is used R2 Predicting time is more Convolution neural network R3 Computationally Expensive Vision –Based Vehicle Detection M.S. Bennet Praba,AP/CSE,SRMIST
- 7. Ref Issue Identified Method or Approach used R9,R10 Worsen sample complexity Policy gradient method R4 Interference Problem Higher Cost More Power Consumption Depends only on sensors and doesn't depend on software(efficient algorithm) R10,R11 Predicting the safe state is not fast enough, False Alarm Intelligent and Advanced Driver Assistance System M.S. Bennet Praba,AP/CSE,SRMIST
- 8. Proposes a framework based on deep reinforcement learning technique To produce a cost effective, accurate and fast enough prediction algorithm to predict the unsafe state M.S. Bennet Praba,AP/CSE,SRMIST
- 9. Collect data like car width, speed , acceleration and velocity from sensor Process the data using neural network Check the threshold level If it exceeds the threshold level, send collision avoidance measures Repeat the process M.S. Bennet Praba,AP/CSE,SRMIST
- 10. Collect data like speed , velocity and acceleration from sensor Process the data using neural network Check the threshold level If it exceeds the threshold level, apply collision avoidance measures Otherwise, Repeat the process Apply suitable collision avoidance algorithm Calculate the car width M.S. Bennet Praba,AP/CSE,SRMIST
- 11. 1.Pinzin long & etal,” Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation”, in IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 656–663, 2017. 2.Michael Everett, Yu Fan Chen, and Jonathan P. “How Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning” arXiv:1805.01956 3.Chen, M. Liu, M. Everett, and J. P. How, “Decentralized, non communicating multiagent collision avoidance with deep reinforcement learning,” in Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017. 4. Y. F. Chen, M. Everett, M. Liu, and J. P. How, “Socially aware motion planning with deep reinforcement learning,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada, September 2017. 5. Shigang Yue, F.Claire Rind, ”Collision detection in complex dynamic scenes using LGMD-Based Visual Neural Network with feature enhancement” in IEEE Transaction on Neural Networks, Vol. 17, No. 3, May 2016. M.S. Bennet Praba,AP/CSE,SRMIST
- 12. 6.Miao Chong, Ajith Abraham and Marcin Paprzycki,”Traffic Accident Analysis Using Machine Learning Paradigms” in Informatica (Slovenia), 2005, pp. 89-98. 7.Richard Bishop,”A Survey of Intelligent Vehicle Applications Worldwide” in Proceedings of the IEEE intelligent Vehicles Symposium, 2000, Dearborn, USA, LCG. 8. Felipe Jimnez, Jos Eugenio Naranjo and scar Gmez, ”Autonomous Manoeuvring Systems for Collision Avoidance on Single Carriageway Roads” in Sensors, 2012 9.Babaeizadeh, Mohammad, Frosio, Iuri, Tyree, Stephen, Clemons, Jason, and Kautz, Jan. GA3C: gpu-based A3C for deep reinforcement learning. arXiv preprint arXiv: 1611.06256, 2016. 10.Espeholt, L., Soyer, H., Munos, R., Simonyan, K., Mnih, V., Ward, T., Doron, Y., Firoiu, V., Harley, T., Dunning, I., Legg, S., and Kavukcuoglu, K. IMPALA: Scalable Distributed Deep-RL with Importance Weighted ActorLearner Architectures. ArXiv e-prints, February 2018. M.S. Bennet Praba,AP/CSE,SRMIST
- 13. 11. McGehee, D., et al. (1998). "Examination of drivers' collision avoidance behavior in a lead vehicle stopped scenario using a front-to-rear-end collision warning system." Contract DTNH93-22-C-07326) Washington, DC: National Highway Traffic safety Administration driver safety. 12. Seiler, P., et al. (1998). "Development of a collision avoidance system." Development 4: 22-17. M.S. Bennet Praba,AP/CSE,SRMIST