A study on latency-guaranteed multi-hop wireless communication system for control of robots and drones

Kagawa, Toshinori; Ono, Fumie; Shan, Lin; Takizawa, Kenji; Li, Huan-Bang; Kojima, Fumihide; Kato, Shigeo

doi:10.1109/wpmc.2017.8301849

Cited by 25 publications

(14 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A user enjoying visuo-haptic perceptions requires not only minimal individual perception delays but also minimal delay variance to avoid motion sickness [14], [15]. A remotely controlled drone or a robotic assembler in a smart factory should always be operational even when the network connection is temporarily unavailable [16]- [18], by sensing and reacting rapidly to the local (and possibly hazardous) environments.…”

Section: Fig 1 Illustration Of Edge ML Where Both Ml Inference and mentioning

confidence: 99%

“…On-chip cache, such as static random access memory (SRAM), has the smallest size, yet it is the fastest, e.g., 24 MB with tens of nanoseconds access latency [110], [111]. Dynamic random access memory (DRAM) is larger but slower than SRAM, e.g., 16 GB with hundreds of nanoseconds access latency [111]. Nonvolatile memory, such as solid-state drive (SSD), is the largest but the slowest, e.g., 30 TB with several microseconds access latency [112].…”

Section: Hardware-model Codesignmentioning

confidence: 99%

“…This implies a regression problem with a 1-Lipshitz function f , which can be solved via supervised learning. (b) Sinkhorn Divergence: Instead of the said dual approach, [153] tackles the primal formulation in (16) with an entropic approximation and the Sinkhorn algorithm [154]. In this approach, the RHS of (16) is recast as infM∈M Tr(MC T ) with the cost matrix C. This is a matching problem of the matrix M given by mini-batched X and Y , which can be solved via the parallelized Sinkhorn algorithm.…”

Section: ) Optimal Transport Theorymentioning

confidence: 99%

See 2 more Smart Citations

Wireless Network Intelligence at the Edge

et al. 2019

View full text Add to dashboard Cite

edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.

show abstract

Section: Fig 1 Illustration Of Edge ML Where Both Ml Inference and mentioning

confidence: 99%

Section: Hardware-model Codesignmentioning

confidence: 99%

Section: ) Optimal Transport Theorymentioning

confidence: 99%

See 1 more Smart Citation

Wireless Network Intelligence at the Edge

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Wi-Fi can provide low cost and high performance user interface [20]. On the other hand, classical Wi-Fi suffers from high contention and short-range communications which result in high multi-hop latency [21] and opens avenue for synchronization attacks [22]. Fortunately, recent standard IEEE 802.11ah extends the transmission range of Wi-Fi and offers support for relaying [8,9].…”

mentioning

confidence: 99%

Efficient Security Scheme for Disaster Surveillance UAV Communication Networks

et al. 2019

View full text Add to dashboard Cite

The Unmanned Aerial Vehicles (UAVs) play a significant role to alleviate the negative impacts of disasters by providing essential assistance to the rescue and evacuation operations in the affected areas. Then, the reliability of UAV connections and the accuracy of exchanged information are critical parameters. In this paper, we propose networking and security architecture for disaster surveillance UAV system. The networking scheme involves a two-tier cluster network based on IEEE 802.11ah, which can provide traffic isolation between the tiers. The security scheme guarantees the accuracy and availability of the collected information from the disaster area applying fingerprint features and data redundancy techniques; the proposed scheme also utilizes the lightweight Ring-Learning with Errors (Ring-LWE) crypto-system to assure the confidentiality of the transmitted data with low overhead. IntroductionUnmanned Aerial Vehicles (UAVs) [1,2] have many military and civilian applications, such as border surveillance, public safety and transportation management. Mainly, UAVs are crucial for rescue and recovery operations during disasters, such as volcanoes and earthquakes, especially when the regular communication networks in the area are partially or completely destroyed. In addition to collecting information about the disaster, UAVs can carry equipment, i.e., medical aids, to the disaster area without involving humans. Other applications for UAV networks could be monitoring the effect of rocket launch operation on the surrounding area [3], preserving public safety during terrorist attacks or natural disasters using 4G [4] or satellite communications [5], prompting the smart farming [6], or utilized in IoT aerial sensing [7].The UAV system could consist of one large drone, as is often the case in military missions, or a group of small drones that are usually cooperating to complete one task, such as traffic monitoring or forest surveillance. Using a swarm of small drones instead of single large drone brings higher system reliability and scalability, but it also introduces additional issues related to management of system components and functions; in particular, it requires the following:1. Central ground substation (CS) which collects data from relaying drones. 2. Clusters of drones participating in the same application that perform some kind of surveillance/sensing application. 3. Cluster head drone(s) in each cluster have two main functions. Firstly, they keep administrative membership data for the cluster. Secondly, they collect sensed data perform data fusion, integrity and confidentiality. Due to a large distance between cluster head(s) and central substation (CS), cluster head(s) do not send data directly to it. Instead, cluster head(s) transmits the data to relay Information 2019, 10, 43 2 of 22drones. Please note that it is also possible that each node in the cluster can communicate with the relay node and that a single or a few nodes keep administrative functions. 4. Relay drones which need to leave the cluster a...

show abstract

“…Provision of wireless infrastructure at disaster sites is a field of active research in disaster robotics. It has been demonstrated that drones can be used to set up multihop networks that allow for remote communication with out-of-sight robots in otherwise communication-deprived locations (Kagawa et al, 2017). Similar solutions should be viable for the cyber-enhanced canine suit platform, although this issue remains to be explored.…”

mentioning

confidence: 99%

An image recognition system aimed at search activities using cyber search and rescue dogs

Arnold

Ohno

Hamada

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

Disaster response presents major challenges for robotics and computer vision alike. The Cyber‐Enhanced Canine Suit is a suit equipped with a camera, Global Navigation Satellite System (GNSS), and various other sensors, to be worn by search and rescue (SAR) dogs for the purpose of enhancing SAR dog operations. This paper presents an image recognition system for use in disaster scenarios and its integration with the Cyber‐Enhanced Canine Suit platform. The system’s intended use is to spot personal items of missing individuals or other visual clues in video streams from various disaster response platforms. The system facilitates quick learning of targets from limited data and makes providing that data quick and easy. It also provides backtrack recognition functionality, to rapidly find novel targets in the seen footage. We evaluated the recognition system on footage gathered in the field, obtaining promising results. Integrated with the Cyber‐Enhanced Canine Suit, the system can automatically plot detections of search targets onto a map display, to provide operators with a quick overview of what was seen where.

show abstract

A study on latency-guaranteed multi-hop wireless communication system for control of robots and drones

Cited by 25 publications

References 3 publications

Wireless Network Intelligence at the Edge

Wireless Network Intelligence at the Edge

Efficient Security Scheme for Disaster Surveillance UAV Communication Networks

An image recognition system aimed at search activities using cyber search and rescue dogs

Contact Info

Product

Resources

About