As a bio-inspired and emerging sensor, an event-based neuromorphic vision sensor has a different working principle compared to the standard frame-based cameras, which leads to promising properties of low energy consumption, low latency, high dynamic range (HDR), and high temporal resolution It poses a paradigm shift to sense and perceive the environment by capturing local pixel-level light intensity changes and producing asynchronous event streams Advanced technologies for the visual sensing system of autonomous vehicles from standard computer vision to event-based neuromorphic vision have been developed In this tutorial-like article, a comprehensive review of the emerging technology is given First, the course of the development of the neuromorphic vision sensor that is derived from the understanding of biological retina is introduced The signal processing techniques for event noise processing and event data representation are then discussed Next, the signal processing algorithms and applications for event-based neuromorphic vision in autonomous driving and various assistance systems are reviewed Finally, challenges and future research directions are pointed out It is expected that this article will serve as a starting point for new researchers and engineers in the autonomous driving field and provide a bird's-eye view to both neuromorphic vision and autonomous driving research communities

Event-Based Neuromorphic Vision for Autonomous Driving: A Paradigm Shift for Bio-Inspired Visual Sensing and Perception

A critical challenge in neuromorphic computing is to present computationally efficient algorithms of learning. When implementing gradient-based learning, error information must be routed through the network, such that each neuron knows its contribution to output, and thus how to adjust its weight. This is known as the credit assignment problem. Exactly implementing a solution like backpropagation involves weight sharing, which requires additional bandwidth and computations in a neuromorphic system. Instead, models of learning from neuroscience can provide inspiration for how to communicate error information efficiently, without weight sharing. Here we present a novel dendritic event-based processing (DEP) algorithm, using a two-compartment leaky integrate-and-fire neuron with partially segregated dendrites that effectively solves the credit assignment problem. In order to optimize the proposed algorithm, a dynamic fixed-point representation method and piecewise linear approximation approach are presented, while the synaptic events are binarized during learning. The presented optimization makes the proposed DEP algorithm very suitable for implementation in digital or mixed-signal neuromorphic hardware. The experimental results show that spiking representations can rapidly learn, achieving high performance by using the proposed DEP algorithm. We find the learning capability is affected by the degree of dendritic segregation, and the form of synaptic feedback connections. This study provides a bridge between the biological learning and neuromorphic learning, and is meaningful for the real-time applications in the field of artificial intelligence.

/pdf/efficient-spike-driven-learning-with-dendritic-event-based-3w52pztv0c.pdf

Efficient Spike-Driven Learning With Dendritic Event-Based Processing.

Vehicle slip angle (VSA) estimation is of paramount importance for connected automated vehicle dynamic control, especially in critical lateral driving scenarios. In this paper, a novel kinematic-model-based VSA estimation method is proposed by fusing information from a global navigation satellite system (GNSS) and an inertial measurement unit (IMU). First, to reject the gravity components induced by the vehicle roll and pitch, a vehicle attitude angle observer based on the square-root cubature Kalman filter (SCKF) is designed to estimate the roll and pitch. A novel feedback mechanism based on the vehicle intrinsic information (the steering angle and wheel speed) for the pitch and roll is designed. Then, the integration of the reverse smoothing and grey prediction is adopted to compensate for the cumulative velocity errors during the relatively low sampling interval of the GNSS. Moreover, the GNSS signal delay has been addressed by an estimation-prediction integrated framework. Finally, the results confirm that the proposed method can estimate the VSA under both the slalom and double lane change (DLC) scenarios.

Automated Vehicle Sideslip Angle Estimation Considering Signal Measurement Characteristic

Deep learning has become the mainstream technology in computer vision, and it has received extensive research interest in developing new medical image processing algorithms to support disease detection and diagnosis. As compared to conventional machine learning technologies, the major advantage of deep learning is that models can automatically identify and recognize representative features through the hierarchal model architecture, while avoiding the laborious development of hand-crafted features. In this paper, we reviewed and summarized more than 200 recently published papers to provide a comprehensive overview of applying deep learning methods in various medical image analysis tasks. Especially, we emphasize the latest progress and contributions of state-of-the-art unsupervised and semi-supervised deep learning in medical images, which are summarized based on different application scenarios, including lesion classification, segmentation, detection, and image registration. Additionally, we also discussed the major technical challenges and suggested the possible solutions in future research efforts.

Recent advances and clinical applications of deep learning in medical image analysis.

The role of shared autonomous vehicle systems in delivering smart urban mobility: A systematic review of the literature

Dynamic Movement Primitives (DMPs) framework is a powerful approach to imitate motor skills, which has outstanding characteristics, such as convergence to the goal position and good imitation performance. Considering complex motion scenes of manipulators, such as changing the goal position or adding obstacles, the original DMPs framework is not sufficient for the requirements. In this paper, we propose a learning control-based hierarchical control strategy to adapt to new goal positions and avoid obstacles: the high-level learning scheme is targeted at imitating the motor skill and generating the optimization trajectory for obstacle avoidance; the lower-level control scheme focuses on the safety and stability of the robot's movement with unknown disturbances. Firstly, the enhanced DMPs framework is presented to imitate the trajectory from human demonstrations, where the novel DMPs can adapt to new goal position with the changing goal, and avoid single or multiple obstacles. Then, the fuzzy adaptive control method is employed to control redundant manipulators, where the fuzzy logic system (FLS) is incorporated to approximate an unknown nonlinear function term of the unknown disturbance. Finally, the effectiveness of the proposed learning-control strategy is demonstrated with simulation results. The results show that the developed hierarchical strategy has good performance for new goal adaptation and obstacle avoidance.

Hu Cao

Papers

Fuzzy Adaptive Control-based Real-time Obstacle Avoidance under Uncertain Perturbations