Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusion

Cai, Peide; Wang, Sukai; Sun, Yuxiang; Liu, Ming

doi:10.1109/lra.2020.2994027

Cited by 54 publications

(41 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-sensor fusion method was designed based on an interpretable neural network for body sensor networks based on communication and data processing with various sensors and robots in medical human-robot interactions. Cai et al [17] presented an autonomous driving system using end-to-end control for autonomous vehicles in various environmental conditions and dynamic obstacles. For this study, the modeling of cars, pedestrians, motorcyclists, and bicyclists had been conducted based on diverse data from multiple domains such as urban and rural areas, traffic densities, weather, and times of the day from cameras, LiDAR, and radar.…”

Section: Large-scale Sensor Fusion For Real-time Event Detectionmentioning

confidence: 99%

“…The significant difference between their work and ours is that we proposed image-based deep learning as scalable multi-sensor fusion while using feature-based deep learning. Cai et al [17] mainly focused on probabilistic model building (without considering edge intelligence) with visual data from cameras, LiDAR and radar, and environmental conditions. In contrast, we focus on edge-based event-detection modeling using visual analytics with real-time sensor data.…”

Section: Large-scale Sensor Fusion For Real-time Event Detectionmentioning

confidence: 99%

“…Lin et al [16] presented smart medical robots and multi-sensor fusion technologies for building human-robot interaction models for realtime monitoring in health care. Cai et al [17] presented the detection of environmental conditions and dynamic obstacles for an autonomous driving system in multiple domains such as urban and rural areas, traffic densities, weather, and times of the day. However, these solutions are specific to a particular context and are not generally applicable to other contexts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Event-Driven Deep Learning for Edge Intelligence (EDL-EI)

Shah

Tariq

Lee

et al. 2021

Sensors

View full text Add to dashboard Cite

Edge intelligence (EI) has received a lot of interest because it can reduce latency, increase efficiency, and preserve privacy. More significantly, as the Internet of Things (IoT) has proliferated, billions of portable and embedded devices have been interconnected, producing zillions of gigabytes on edge networks. Thus, there is an immediate need to push AI (artificial intelligence) breakthroughs within edge networks to achieve the full promise of edge data analytics. EI solutions have supported digital technology workloads and applications from the infrastructure level to edge networks; however, there are still many challenges with the heterogeneity of computational capabilities and the spread of information sources. We propose a novel event-driven deep-learning framework, called EDL-EI (event-driven deep learning for edge intelligence), via the design of a novel event model by defining events using correlation analysis with multiple sensors in real-world settings and incorporating multi-sensor fusion techniques, a transformation method for sensor streams into images, and lightweight 2-dimensional convolutional neural network (CNN) models. To demonstrate the feasibility of the EDL-EI framework, we presented an IoT-based prototype system that we developed with multiple sensors and edge devices. To verify the proposed framework, we have a case study of air-quality scenarios based on the benchmark data provided by the USA Environmental Protection Agency for the most polluted cities in South Korea and China. We have obtained outstanding predictive accuracy (97.65% and 97.19%) from two deep-learning models on the cities’ air-quality patterns. Furthermore, the air-quality changes from 2019 to 2020 have been analyzed to check the effects of the COVID-19 pandemic lockdown.

show abstract

Section: Large-scale Sensor Fusion For Real-time Event Detectionmentioning

confidence: 99%

Section: Large-scale Sensor Fusion For Real-time Event Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Event-Driven Deep Learning for Edge Intelligence (EDL-EI)

Shah

Tariq

Lee

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Developing an effective multi-model fusion method enhances the data efficiency of environment, which improves the perception [120] of artificial agents to cope with dynamic and complex environments. Therefore, a visual DRL navigation agent with a multi-modal sense can learn a better policy [121]. Based on multi-modal information, an artificial agent has good adaptability to dynamic and complex environments, which helps to improve the generalization of navigation model.…”

Section: ) Multi-modal Fusionmentioning

confidence: 99%

A Survey on Visual Navigation for Artificial Agents With Deep Reinforcement Learning

Zeng

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Visual navigation (vNavigation) is a key and fundamental technology for artificial agents' interaction with the environment to achieve advanced behaviors. Visual navigation for artificial agents with deep reinforcement learning (DRL) is a new research hotspot in artificial intelligence and robotics that incorporates the decision making of DRL into visual navigation. Visual navigation via DRL, an end-to-end method, directly receives the high-dimensional images and generates an optimal navigation policy. In this paper, we first present an overview on reinforcement learning (RL), deep learning (DL) and deep reinforcement learning (DRL). Then, we systematically describe five main categories of visual DRL navigation: direct DRL vNavigation, hierarchical DRL vNavigation, multi-task DRL vNavigation, memory-inference DRL vNavigation and vision-language DRL vNavigation. These visual DRL navigation algorithms are reviewed in detail. Finally, we discuss the challenges and some possible opportunities to visual DRL navigation for artificial agents.

show abstract

“…Sensor detection is undergoing a transition from an independent style to a cooperative style, and sensor networks have found increasing numbers of applications in areas such as in the Internet of Things [1], environmental monitoring [2], cooperative radar detection [3] and autonomous driving [4]. According to the types of communication topologies, sensor networks are classified into centralized networks and distributed networks [5].…”

Section: Introductionmentioning

confidence: 99%

Distributed Kalman Filtering Based on the Non-Repeated Diffusion Strategy

Zhang

Shen

2020

Sensors

View full text Add to dashboard Cite

Estimation accuracy is the core performance index of sensor networks. In this study, a kind of distributed Kalman filter based on the non-repeated diffusion strategy is proposed in order to improve the estimation accuracy of sensor networks. The algorithm is applied to the state estimation of distributed sensor networks. In this sensor network, each node only exchanges information with adjacent nodes. Compared with existing diffusion-based distributed Kalman filters, the algorithm in this study improves the estimation accuracy of the networks. Meanwhile, a single-target tracking simulation is performed to analyze and verify the performance of the algorithm. Finally, by discussion, it is proved that the algorithm exhibits good all-round performance, not only regarding estimation accuracy.

show abstract

Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusion

Cited by 54 publications

References 18 publications

Event-Driven Deep Learning for Edge Intelligence (EDL-EI)

Event-Driven Deep Learning for Edge Intelligence (EDL-EI)

A Survey on Visual Navigation for Artificial Agents With Deep Reinforcement Learning

Distributed Kalman Filtering Based on the Non-Repeated Diffusion Strategy

Contact Info

Product

Resources

About