On Reliable Neural Network Sensorimotor Control in Autonomous Vehicles

This paper deals with (deep) neural network implementations of sensorimotor control for automated driving. We show how to construct complex behaviors by re-using elementary neural network building blocks that can be trained and tested extensively; one of our goals is to mitigate the “black box” and verifiability issues that affect end-to-end trained networks. By structuring complex behaviors within a subsumption architecture, we retain the ability to learn (mostly at motor primitives level) with the ability to create complex behaviors by subsuming the (well-known) learned elementary perception-action loops. The learning process itself is simplified, since the agent needs only to learn elementary behaviors. At the same time, the structure imposed with the subsumption architecture ensures that the agent behaves in predictable ways (e.g., treating all obstacles uniformly). We demonstrate these ideas for longitudinal obstacle avoidance behavior, but the proposed approach can also be adapted to other situations.

[1]  Gösta H. Granlund,et al.  Channel Representation of Colour Images , 2002 .

[2]  Forrest N. Iandola,et al.  SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  David Windridge,et al.  Exploiting dream-like simulation mechanisms to develop safer agents for automated driving: The “Dreams4Cars” EU research and innovation action , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[5]  Adrian Weller,et al.  Challenges for Transparency , 2017, ArXiv.

[6]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[7]  David Windridge,et al.  Artificial Co-Drivers as a Universal Enabling Technology for Future Intelligent Vehicles and Transportation Systems , 2015, IEEE Transactions on Intelligent Transportation Systems.

[8]  David A. Forsyth,et al.  NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles , 2017, ArXiv.

[9]  R. VanRullen.  Perception Science in the Age of Deep Neural Networks , 2017, Front. Psychol..

[10]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[11]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[12]  Jianxiong Xiao,et al.  DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[14]  John Tran,et al.  cuDNN: Efficient Primitives for Deep Learning , 2014, ArXiv.

[15]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[16]  Dawn Song,et al.  Robust Physical-World Attacks on Deep Learning Models , 2017, 1707.08945.

[17]  Jagannathan Sarangapani,et al.  Neural Network Control of Nonlinear Discrete-Time Systems , 2018 .

[18]  Seyed-Mohsen Moosavi-Dezfooli,et al.  Robustness of classifiers: from adversarial to random noise , 2016, NIPS.

[19]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[20]  Sameer Singh,et al.  “Why Should I Trust You?”: Explaining the Predictions of Any Classifier , 2016, NAACL.

[21]  Chang Liu,et al.  Learning a deep neural net policy for end-to-end control of autonomous vehicles , 2017, 2017 American Control Conference (ACC).

[22]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[24]  David A. Forsyth,et al.  SafetyNet: Detecting and Rejecting Adversarial Examples Robustly , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Bernd Spanfelner,et al.  Challenges in applying the ISO 26262 for driver assistance systems , 2012 .

[26]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[27]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[28]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[29]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[30]  Luca Rigazio,et al.  Towards Deep Neural Network Architectures Robust to Adversarial Examples , 2014, ICLR.

[31]  Peter Redgrave,et al.  Layered Control Architectures in Robots and Vertebrates , 1999, Adapt. Behav..

[32]  Elizabeth Gibney,et al.  Google AI algorithm masters ancient game of Go , 2016, Nature.

[33]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[34]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[35]  J. Kalaska,et al.  Neural mechanisms for interacting with a world full of action choices. , 2010, Annual review of neuroscience.

[36]  Nidhi Kalra,et al.  Driving to Safety , 2016 .

[37]  Vidya N. Murali,et al.  DeepLanes: End-To-End Lane Position Estimation Using Deep Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[38]  Trevor Darrell,et al.  Generating Visual Explanations , 2016, ECCV.

[39]  M. Felsberg,et al.  The B-Spline Channel Representation: Channel Algebra and Channel Based Diffusion Filtering , 2002 .

[40]  Michael Felsberg,et al.  Channel smoothing: efficient robust smoothing of low-level signal features , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Sai Chand,et al.  Autonomous Vehicles: Disengagements, Accidents and Reaction Times , 2016, PloS one.

[42]  Ernst D. Dickmanns,et al.  Vehicles Capable of Dynamic Vision , 1997, IJCAI.