Future vehicles: learnable wheeled robots

Abstract

As one of the important signs of the third wave of artificial intelligence, wheeled robots not only inherit knowledge but also learn independently, which brings about to learnable wheeled robots that use a driving brain to achieve data-driven control and learning. Presently, most existing technologies for selfdriving vehicles can learn positively from the benchmark drivers to guarantee safe driving. However, in many unpredicted situations, such as rollover, human drivers often cause the behavior of irrational subconscious on account of human emotions like panic. In this paper, we propose a learnable wheeled robot using the driving brain by taking the rollover as an example, which is the most serious and dangerous situation in dynamic vehicle operations. Then, based on the analysis of rollover accidents, we utilize the driving brain reversely and conduct negative learning, materializing, and condensing the group intelligence of accident experts, to solve the problem of the lack of individual intelligence in emergencies and further promote real-time response to other dangerous conditions, such as puncture for self-driving vehicles.

Retracted: Multi‐vehicle group‐aware data protection model based on differential privacy for autonomous sensor networks

“…In order to solve the threat to user privacy caused by low security of connected vehicles, the sensitive data privacy protection scheme of connected vehicles based on blockchain can improve the hiding rate of sensitive data, ensure the information security of intelligent vehicles, and better serve the architecture of Internet of vehicles [9]. As one of the essential signs of the third wave of artificial intelligence, wheeled robots not only inherit knowledge but also learn independently, which brings about to enable wheeled robots that use a driving brain to achieve data-driven control and learning [10]. In the process of learning and interaction of wheeled robots, the privacy protection of the generated data will face substantial challenges due to its large data volume and diverse structure, and the privacy computing field will be paid additional attention in the future [11].…”

A Survey of Human Action Recognition and Posture Prediction

“…Compared with the latest data, the experimental results of the benchmark dataset show that the northwest UCLA and MCAD datasets increased by 3% and 2%, respectively. These methods can be used in intelligent video surveillance, human-computer interaction, video retrieval and other applications [1,[144][145][146] . In 2021, Wang et al [147] proposed a recurrent neural network for spatiotemporal predictive learning (PredRNN) to learn sequential actions.…”

“…The development of human society in recent years is known as the "AI Era", in which the development of intelligent technology needs self-learning and selfcognition abilities [1] . The study of human action recognition and posture prediction enables machines to understand human behaviors and intentions and has been Nan Ma and Zhixuan Wu are with the Beijing Key Laboratory of Information Service Engineering, the College of Robotics, Beijing Union University, Beijing 100101, China.…”

DSA: Deformable Segmentation Attention for Multi-Scale Fisheye Image Segmentation

“…There are now two approaches to dealing with it. The first is to fix first and then segment [3]; this way simplifies the entire problem in order to increase the fisheye image corection impact, decreasing the difficulty of design. For example, Yang [4] proposed an algorithm for improving the seherical projection model to enhance the edge correction capability, while Ma [5] proposed a correction algorithm based on a mapping adaptive convolution and isometric projection model to perform secondary correction of the projected image.…”