October 17, 2021

Subscribe
Linkedin-in Twitter Facebook-f Youtube Instagram

Join our PHYSICAL Singapore OpenGov Leadership Forum 2021 - Click here for more details

We are creating some awesome events for you. Kindly bear with us.

Taiwan to Build Rocket Launch Site

Image credits: focustaiwan.tw
Share via

The Head of the National Space Organisation (NSO) stated that the Taiwanese government plans to build a rocket launch site for the long-term development of the country’s space programme. The plans were disclosed after the Taiwan-based commercial rocket company sought and gained approval to launch its first domestically built rocket in Australia.

According to a statement, the company will conduct a test flight of its Hapith I — a 10m, two-stage, sub-orbital science rocket — from the Whalers Way Orbital Launch Complex, which is operated by Southern Launch. The Head of NSO said that the company had been scheduled to launch the Hapith I rocket at a site in Nantian Village, Taitung County, Taiwan, but the plan was suspended because of legal disputes.

The NSO then came up with a plan for the company to launch its research rocket at a site in southern Pingtung’s Mudan Township, but before the proposal could be approved, the company turned to Australia and obtained approval there.

Taiwan’s government, however, has a long term plan to build a rocket launch site. Taiwan’s Ministry of Science and Technology (MOST) last year released a set of security guidelines for the launch of research rockets.

According to the guidelines, the site in Mudan Township has been designated as a short term project for rocket launches, but that plan has not yet been finalised, as negotiations with the residents there are still in progress. The NSO’s ultimate goal is to build a permanent national rocket launch site for the long term development of the nation’s space programme.

The planning for that launch site is expected to begin next year, after the expected passage of a draft bill on the country’s future space development, which was put forth by MOST. If the bill is passed, it will allow for the upgrade of the NSO to an independent agency directly under the science and technology ministry, noting that currently, it is one of eight research centres under MOST’s National Applied Research Laboratories.

According to a page, the primary focus of Taiwan’s Long-term National Space Technology Development Programme is satellite development. Having laid the foundation for indigenous space technology in the first and second phases of the programme, the nation is now launching the third phase, which will run from 2019 to 2028.

The programme aims to push domestic aerospace technology to new heights and meet the challenges of cutting-edge space missions. At the same time, the programme also aims to extend and spread the benefits of the aerospace technology industry, nurture space technology talent, and build an aerospace industry supply chain of Taiwan’s own.

As reported by OpenGov Asia, Taiwan is stepping up efforts to tap into the global aerospace market, with a particular focus on developing a specific kind of satellite. Among different market segments, those related to the development of Low Earth Orbit (LEO) satellites are particularly worth pursuing for Taiwan. Those satellites, often designed in constellations, have a shorter life cycle — between two to four years, compared with larger ones and therefore offer more of an opportunity for Taiwanese businesses.

In addition, LEO satellites are crucial to the development of the Internet of Things (IoT), which has been pursued by global technology and communications heavyweights. That is because the relatively inexpensive LEO communication satellites can be launched in large enough numbers to economically provide sufficient bandwidth for the data transmission required by the IoT.

The space development promotion act is expected to help. The act, which will regulate the country’s space-based activities, shows the world Taiwan’s ambition to carve out its own niche in the space economy.

NSW Technology Response to Focus on Firefighter Safety

Image Credits: NSW Government, Press Release
Share via

The ‘connected firefighter’ package is a $57.4 million investment as part of the New South Wales (NSW) government’s response to the Independent Bushfire Inquiry following the Black Summer Bushfires of 2019/20. The package includes:

  • Remotely Piloted Aircraft Systems (RPAS), or drones that provide images and data from incidents in real-time, assist firefighters with incident planning.
  • Cell on Wheels (CoWs), which are mobile modules that are equipped with communications technology and provide power for extended periods in remote parts of the state without coverage.
  • Upgrades to Fire and Rescue NSW Mobile Command Centres for communications between incident management teams and firefighters.
  • Vehicle as a Node (VaaNs), vehicles that have a built-in Wi-Fi hub to provide mobile 4G network in remote locations where satellite connection is limited.

The region’s Police and Emergency Services Minister said that the NSW Government is providing record funding towards initiatives that are bolstering the safety of the community. It is apparent is that the emergency services are entering a tech boom, one which rightly puts NSW ahead of the pack this bushfire season, he said. These assets will ensure NSW’s first responders are safe as they enter dangerous and volatile fire grounds to protect their communities.

A report from earlier this year noted that Emergency services and communities will be better prepared for disaster, with another record $1.9 billion budget in 2021-22 across the NSW Rural Fire Service (NSW RFS), Fire and Rescue NSW (FRNSW), and NSW State Emergency Service (NSW SES).

The Minister for Police and Emergency Services has confirmed a record investment of $930 million for FRNSW and $240 million for NSW SES reflected the Government’s continued focus on safeguarding lives, property and supporting emergency management personnel. The budget includes more than $75 million over four years for the Stay Safe and Keep Operational program across emergency services, which will support the communication requirements of the emergency services agencies in areas not serviced by the Government Radio Network.

Fire and Rescue NSW will benefit from a nearly $23 million investment over four years for the rollout of new firefighting personal protective clothing. Almost $12 million will be spent over two years for the completion of FRNSW fire stations at Marsden Park and Oran Park, including trucks and equipment for each station.

The funding also includes an additional $268 million to continue the implementation of the recommendations of the NSW Independent Bushfire Inquiry, building on more than $192 million already announced since the 2019-20 bushfire season.

The funding package includes:

  • More than $48 million for fleet replacement and vehicle safety retrofits for frontline firefighting agencies;
  • $16 million for additional NSW RFS crews for hazard reduction and mitigation works;
  • More than $34 million to accelerate the delivery of the strategic fire trails network;
  • More than $18 million over two years to enhance coordination between emergency services, helping to fast-track integrated call and dispatch at FRNSW;
  • More than $17 million over two years to operationalise two black hawk helicopters and to replace an existing NSW RFS helicopter;
  • $20 million over two years for NSW RFS to upgrade Fire Control Centres, Emergency Operations Centres, and Station/Neighbourhood Safe Places;
  • Nearly $7 million to enhance firefighter safety through fire ground tracking, training and accreditation of heavy plant machinery over four years; and
  • More than $5 million to acquire additional drones for firefighting operations by FRNSW.

The NSW RFS will benefit from a $686 million budget in 2021-22, which will ensure it has the resources required to provide a world-leading bushfire response capability. The Budget also includes almost $790 million for Resilience NSW to coordinate and oversee whole-of-government disaster management, recovery, and build resilience to disasters.

IIT-Hyderabad, ARAI Ink MoU for Autonomous Vehicle Technology

Share via

The Indian Institute of Technology in Hyderabad’s (IIT-Hyderabad) Technology Innovation Hub on Autonomous Navigation (TiHAN) has signed a memorandum of understanding (MoU) with the Automotive Research Association of India (ARAI). They will collaborate in the field of India-specific technology development, simulations, and the real-world verification and validation of advanced driver assistance systems and autonomous driving. TiHAN and ARAI will jointly promote research and develop and offer solutions, technologies, and practices to the industry to enable smart mobility in autonomous vehicles.

The collaboration will significantly contribute to safe and sustainable autonomous mobility solutions in India and provide greater insight into TiHAN activities. It will update testbeds on autonomous navigations (aerial/terrestrial) in the campus, the Project Director of TiHAN-IIT-H stated. The collaboration will also promote the innovation ecosystem, skill development, and entrepreneurship activities in the area of autonomous navigation systems.

According to an official statement, the partnership will further strengthen ARAI’s abilities and activities in the field of smart mobility. ARAI has been looking for avenues to disseminate knowledge in a structured way and is keen to offer joint programmes, the ARAI Director noted.

TiHAN at IIT-H focuses on the research, design, and development of autonomous navigation and data acquisition systems for UAVs (unmanned aerial vehicles) and RoVs (remotely operated underwater vehicles), etc. An official said that TiHAN aims to support activities related to autonomous navigation, which will make India a leader in the domain. TiHAN intends to be at the forefront in devising technology, protocols, testing, and validation through testbed, which will be inaugurated shortly.

Recently, IIT-Hyderabad announced it is investing more than IN₹10 million (US$133,406) in six start-ups that are working in the areas of autonomous navigation. A news report stated that these deep-tech start-ups largely work on building drones, an autonomous indoor logistics ecosystem for warehousing, and surveillance UAVs, etc. The prototype-ready start-ups, which are working on projects like building sentient drones, an autonomous indoor logistics ecosystem for warehousing, ecological monitoring using drones, would get IN₹2.5 million (US$33,351) each.

Apart from this, TiHAN is also investing up to IN₹1 million (US$13,341) in early-stage start-ups, including a project that is building surveillance UAVs, another that is making drones for video and photo applications, and a project that is working on passive thermal cooling systems for li-ion battery packs. In addition to the start-ups, these facilities will also be available for researchers and the industry at large, an official noted. TiHAN is going to support more deep-tech start-ups in the coming months.

In September, ARAI indigenously developed a charger for electric vehicles (EV) to boost the EV ecosystem in the country. To promote EVs, charging infrastructure is crucial, since mobility chargers are imported, the association’s focus is to develop these indigenously, which will be cost-effective and boost the local economy, the ARAI Director noted. He was speaking at a press conference organised to announce the details of the Symposium on International Automotive Technology (SIAT 2021). Many EV components, including motors, controllers, and chargers are imported. ARAI has developed indigenous technology for EV charger AC001, which has been taken up for manufacturing and promotion by Bharat Electronics. The charging points will be set up by Bharat Electronics and parts for EV charger systems will be manufactured locally.

Taiwan Highlights Key Tech Sectors to Drive Post-pandemic Economy

Share via

The post-pandemic world is entering a period characterised by restructuring and consolidation. Taiwan’s Ministry of Science and Technology (MOST), with the backing of Academia Sinica, the Ministry of Education and the Ministry of Health and Welfare are focused on six key strategic industries: IT and digitisation, cybersecurity, precision healthcare, renewable and sustainable energies, national defence and strategy, as well as civilian affairs and military preparedness.

With the rising popularity of the 5G infrastructure, asset security will be the next global battlefield. The synergy between Artificial Intelligence (AI), Internet of Things (IoT), cloud and many other emerging technologies related to 5G is yielding a plethora of innovative cross-domain applications. With the popularity of 5G, asset security has become a critical issue that cannot be ignored.

Healthcare and technologies join hands to pave the way for the rise of precision healthcare. As the ageing society is creating a growing demand for medical services and management of chronic diseases, precision healthcare has become an irreversible trend worldwide. A number of leading medical institutions are utilising advanced technologies to enhance their smart healthcare and smart hospital services.

Taipei Veterans General Hospital President said that he intends to make smart healthcare the centrepiece of the next stage of development at the hospital, with the goal of reaching a peak utilisation of cutting-edge technologies that combine precision healthcare and big data.

Science and technology help improve military power by speeding up the transformation of the defence industry. When it comes to defence and strategy, Taiwan has accumulated substantial experience as a result of having developed the FORMOSAT-5 satellite and the FORMOSAT-7 satellite constellation, in combination with its existing complete supply chains and manufacturing capabilities in the semiconductor, information communication electronics and precision machinery sectors

These technologies assure Taiwan an ongoing capability to develop and manufacture satellites, as well as serving as an important R&D and manufacturing base for global satellite components, ground communications, ground terminals and other equipment.

Taiwan has long held an edge in display technology, and the sector is an economic powerhouse. To take full advantage of the nearly limitless opportunity presented by internet-connected devices and application services, and position display technologies and related applications as the engine for Taiwan’s next wave of economic growth, the government has released an action plan for display technologies and applications covering the years 2020 to 2024.

This strategy will move the sector beyond mere displays toward the 2030 vision of a smart-tech lifestyle incorporating emerging display technologies and applications, thereby keeping Taiwan’s advanced tech industry at the global forefront.

Three are three essential Taiwan tech strategies:

  • Encourage demonstration applications and field testing: Drive domestic demand by building demonstration sites for exemplary solutions incorporating domestic products. Build Taiwan into the world’s top supplier of display technology products and solutions by 2030.
  • Develop new capabilities for smart technology: Develop emerging technologies like intelligent sensors, online-offline convergence, and cybersecurity, as well as advance new technology through multidisciplinary cooperation. Elevate Taiwan’s international competitiveness and position on the value chain by producing a range of specialised and differentiated products by 2030.
  • Build an environment for industrial development: Construct communications mechanisms and experimentation platforms for smart retail, smart transport, smart health care and smart entertainment. Nurture new talent capable of synthesising multidisciplinary research to create future-oriented display technologies and innovative applications, and promote cooperation with international counterparts.

Taiwan researchers have been inventing novel advanced technologies, including a bendable water-enabled portable power bank — a device that generates power from a few drops of water. As reported by OpenGov Asia, a team from the National Taiwan University of Science and Technology said that the gadget utilises membrane technology to generate electricity from water.

Self-driving Cars with New Smart Solutions in China

Image source: chinadaily.com
Share via

A Chinese tech giant has opened up its self-driving robo-taxis to the public on the streets of Shanghai. Passengers are able to hail one of the autonomous taxis at around 150 stations throughout the city’s Jiading area, a residential and commercial part of Shanghai. As the system is currently in a testing phase, the service is free and will operate from 9.30 pm to 11 pm daily through an app.

The autonomous taxis feature a combination of lidar, radar, cameras and GPS — similar to set-ups used by other self-driving technology companies, making them capable of Level 4 autonomy. This would mean that, in most cases, the vehicle does not require human interaction and can fully drive itself. A human overseer will, nevertheless, be on standby at all times during the Shanghai trials.

Autonomous vehicles have accumulated over 8.7 million miles of testing. Its goal is to put around two hundred vehicles on Shanghai’s roads in the near future and says that it is either testing or deploying five hundred vehicles across thirty cities. Shanghai is the fifth city in which the service has been rolled out after Guangzhou, Changsha, Cangzhou and Beijing, all cities with populations over 6.5 million.

The service has also expanded to Beijing as fully driverless robo-taxis began operating last April. The robo-taxis have an operator sitting in the passenger seat, rather than behind the wheel, in order to reassure passengers. Rides in Beijing cost 30 yuan (around £3.40), though elsewhere journeys remain free, as the system is still in its testing phase.

Apart from self-driving taxis, a leading Chinese autonomous driving firm has also unveiled its latest L4-level unmanned delivery vehicles and smart solutions recently, as self-driving commercialisation is revving up in the country with faster-than-expected driverless applications.

The latest unmanned delivery vehicles have already offered delivery services in communities in foreign markets, and are able to cope with complex scenarios of open roads in urban villages, urban-rural junctions as well as downtown areas. The unmanned delivery vehicles have been applied to sectors like automobile manufacturing, hazardous chemicals, food processing, agricultural breeding, civil aviation and industrial parks.

In China, a sound unmanned distribution business model has been formed with technologies able to support different needs. The overall industry is expected to eventually enjoy large-scale commercial applications.

For some time now, domestic tech companies have been gearing up efforts in unmanned delivery services, which are expected to generate huge commercial value in a variety of businesses like express delivery, food takeaway orders, fresh produce ordering and retail pharmaceuticals.

Beijing also issued temporary self-driving license plates to 99 vehicles from 15 companies including online food delivery giants, self-driving firms and ride-hailing platforms, which marked a milestone for the commercialisation of autonomous driving.

As reported by OpenGov Asia, the Ministry of Transport (MOT) and the Ministry of Science and Technology jointly issued a guideline mapping out key transport technology based on innovation for China through 2035. The guideline emphasises making technological breakthroughs in the transport sector. It sets the goal that self-reliance on key transport technology will be achieved by 2035. Mechanisms will optimise to spur the vitality of innovative entities as much as possible. Legislation in artificial intelligence (AI), autonomous driving, and unmanned aerial vehicles (UAV) will be studied and drawn up.

Though the smart public transport service is currently limited to selected areas, they have been tried in a variety of application scenarios such as residential communities, commercial areas, and industrial parks to increase transportation efficiency and save fuel consumption.

The demonstration pioneers have been constantly fine-tuning and upgrading the systems while extending the mileage of safe operation, increasing the number of passengers, pouring investment in technology upgrading, and infrastructure construction to cope with the demand for intelligent public transport.

Disinfection Robots Deployed in Singapore’s Healthcare Facilities

Share via

Singapore’s Tampines Polyclinic, this month will use robots instead of nurses to monitor patients’ temperatures and remind them to put on their masks. The Healthcare Assistive Robot for Frontline Infection Control (Hiro) was developed by researchers at Ngee Ann Polytechnic (NP) and is currently being tested at the polyclinic. The robot uses UV-C light to kill bacteria and viruses and can direct visitors to service points.

NP’s Robotics Research and Innovation Centre assistant director said, “the robot is meant to help cut down on the possibility of infection in the polyclinics and also reduce the burden on healthcare staff doing laborious tasks like cleaning hard-to-reach areas and temperature screening, especially during the Covid-19 pandemic.”

We want this facility to be a platform for collaboration with the industry as NP moves towards our vision of helping to develop technology for the future in the healthcare, transportation, construction and sustainability industries.

– Assistant Director, Robotics Research and Innovation Centre, Ngee Ann Polytechnic

The Healthcare Assistive Robot is part of the NP’s joint effort with healthcare provider SingHealth, which operates eight of the 20 polyclinics in the area. The robot’s development began last year, with plans to deploy more at various SingHealth polyclinics the following year. NP also announced the launch of the Robotics Research and Innovation Centre, which is divided into two wings and located on NP’s Clementi Road campus. The centre will house students pursuing a new Specialist Diploma in Robotics Engineering, which is geared toward adult learners and will accept 40 applicants in April of next year.

The facilities, which include workshops, showcase areas, and laboratories, will provide students with real-world robotics experience, according to the NP deputy principal. Moreover, other projects in the works with the National Parks Board include a park patrol robot and a plant health monitoring robot (NParks). Last year, in collaboration with Hougang Primary School, CoDDiE, a teaching assistant robot that assists students in learning to code, was developed. As a result of the Covid-19 pandemic, a variety of unmanned robots have begun to appear in public roles across the country.

OpenGov Asia in an article reported that two robots have been patrolling the Toa Payoh Central neighbourhood in Singapore as part of a three-week trial, looking for errant smokers, unlicensed hawkers, motorbikes and e-scooter riders on sidewalks and gatherings that exceed the current group size limits. The robots are designed to alert public officers in real-time to these offences since they will be equipped with cameras that have a 360-degree field of vision and can see in the dark. They will also be able to broadcast and show warnings warning people about the dangers of such behaviour.

The patrolling robot, developed by HTX in collaboration with the Agency for Science, Technology, and Research, will contribute to enhancing efficiency while reducing the need for manpower for foot patrols, according to the company. This is particularly true for labour-intensive operations like monitoring illegal hawkers. The latest patrolling robot is a refresh of the police’s Multi-purpose All-Terrain Autonomous Robots, or Matar, which have been deployed at large public events such as the National Day Parade, Marina Bay Countdown, and Chingay.

The fourth industrial revolution’s technological innovations are radically transforming the economy. The self-sufficient economy is becoming a reality. AI, robotics, and the Internet of Things (IoT) advancements are ushering in a new era of automation.

Workplace automation in Singapore is expected to increase more than double in three years, covering 29% of all work done by businesses, up from 14% in 2018. This could result in at least 5% of Singapore’s full-time workers losing their jobs.

Singapore must adopt new strategies to keep up with global technological advancements to avoid falling behind. The automation of the economy will be critical to Singapore’s growth and competitiveness. According to a report, automation could boost global productivity growth by up to 1.4% per year. However, for the Singaporean workforce, automation may pose significant challenges and disruptions to current jobs and skillsets.

Powering Vaccinations with Tech to Spur Philippine Economy

Share via

According to new data released by the United Nations Development Programme (UNDP), the World Health Organisation (WHO), and the University of Oxford, COVID-19 vaccine inequity will have a long-term and profound impact on socioeconomic recovery in low- and lower-middle-income countries unless urgent action is taken to increase supply and ensure equitable access for all countries, including through dose sharing.

Despite lower growth projections for the next two years, Asean+3 Macroeconomic Research Office (AMRO) economists in the Philippines said what is important is that the government has increased its vaccination programme against Covid-19. Whereas the Governor of the Bangko Sentral ng Pilipinas (BSP) stated that an increase in the number of people vaccinated against coronavirus will address the country’s pandemic-related unemployment.

Increased vaccination drive would help the country gradually win the war vs. the unseen enemy, which is Covid-19. Full vaccination sharply reduces the risk of Covid-19 infections, severe cases or hospitalisation, and deaths, thereby reducing the burden on the health care system and correspondingly reduces the risk of lockdowns, going forward.

– Commercial Banking Corporation 

“I think it’s very important but to me, the key here really is our vaccine turnout and we have been doing very well now,” he said during a virtual event. The country’s unemployment rate rose to 8.1% in August, up from 6.9% in July. Economic managers predicted the increase due to the implementation of stricter quarantine restrictions following the increase in Covid-19 cases caused by the Delta variant. However, they reported that labour force participation increased to 63.6% in August from 59.8% the previous month as more people rejoined the labour force.

The chief economist of Commercial Banking Corporation (RCBC) noted that the continued vaccination drive and reopening of the economy bode well for the country’s economic recovery prospects in the coming quarters or even years, albeit gradually, given the need to reduce new COVID-19 cases amid risks associated with the unvaccinated.

“The country’s economy could return to pre-COVID levels as early as the latter part of 2022 or by 2023, but the recovery of other businesses/industries, especially those hard-hit by the pandemic last year, would take much longer,” he added.

In addition, the Department of Information and Communications Technology (DICT) recently launched the National Digital Vaccine Certificate to unify all LGU-issued vaccination cards across the country (VaxCertPH). VaxCertPH is a component of the DICT’s Vaccine Information Management System (VIMS), and its ultimate goal is to enable the National COVID-19 Vaccination Operations Centre to vaccinate as many people as possible in the shortest amount of time.

The system is claimed to be reliant on data given by the LGUs to the central VIMS data warehousing for the purposes of generating a digital certificate. All data is safeguarded by the relevant encryptions and can be validated by authorised agencies, groups or countries cryptographically.

OpenGov Asia reported in an article stating that the government is also intensifying the Prevent, Detect, Isolate, Treat, and Recover (PDITR) strategy during the lockdown periods to facilitate the reopening of the economy. To strengthen the ‘detect’ and ‘isolate’ pillars, NEDA, the Department of Health (DOH), and other local government units (LGUs), with the help of data scientists from the Asian Institute of Management, are working on a solution to automatically determine likely close contacts of COVID-19 positive cases and immediately notify these people via text message.

Speaking at the recent Philippine OpenGov Leadership Forum, Denis F. Villorente, Undersecretary for the National Information & Communications Technology Assets Index, Department of Information and Communications Technology (DICT), spoke about the potential of a robust national ID system that could facilitate multiple types of transactions necessary for digital ecosystems and societies, saving people, government and businesses time and money and unlock new drivers of economic value and growth.

AI Learns Cause and Effect of Navigations Tasks

business man hand holding a touch pad computer and 3d streaming images
Share via

Artificial Intelligence (AI) can learn to solve all sorts of problems, but whether these powerful, pattern-recognising algorithms actually understand the tasks they are performing remains an open question. Researchers at MIT have now shown that a certain type of AI can learn the true cause-and-effect structure of the navigation task it is being trained to perform.

Because these networks can understand the task directly from visual data, they should be more effective than other neural networks when navigating in a complex environment, like a location with dense trees or rapidly changing weather conditions. In the future, this work could improve the reliability and trustworthiness of machine learning agents that are performing high-stakes tasks, like driving an autonomous vehicle on a busy highway.

Because these brain-inspired machine-learning systems are able to perform reasoning in a causal way, we can know and point out how they function and make decisions. This is essential for safety-critical applications.

– Ramin Hasani, Co-lead Author, Computer Science and Artificial Intelligence Laboratory

The new research draws on previous work in which the researchers showed how a brain-inspired type of deep learning system called a Neural Circuit Policy (NCP), built by liquid neural network cells, is able to autonomously control a self-driving vehicle, with a network of only 19 control neurons.

The researchers observed that the NCPs performing a lane-keeping task kept their attention on the road’s horizon and borders when making a driving decision, the same way a human would while driving a car. Other neural networks they studied did not always focus on the road.

They found that, when an NCP is being trained to complete a task, the network learns to interact with the environment and account for interventions. In essence, the network recognises if its output is being changed by a certain intervention, and then relates the cause and effect together.

During training, the network is run forward to generate an output, and then backwards to correct for errors. The researchers observed that NCPs relate cause-and-effect during forward-mode and backward-mode, which enables the network to place very focused attention on the true causal structure of a task.

The researchers tested NCPs through a series of simulations in which autonomous drones performed navigation tasks. Each drone used inputs from a single camera to navigate. The drones were tasked with travelling to a target object, chasing a moving target, or following a series of markers in varied environments, including a redwood forest and a neighbourhood. They also travelled under different weather conditions, like clear skies, heavy rain, and fog.

The researchers found that the NCPs performed as well as the other networks on simpler tasks in good weather, but outperformed them all on the more challenging tasks, such as chasing a moving object through a rainstorm.

NCPs are the only network that pay attention to the object of interest in different environments while completing the navigation task, wherever you test it, and in different lighting or environmental conditions. This is the only system that can do this casually and actually learn the behaviour the researchers intend the system to learn.

Once the system learns what it is actually supposed to do, it can perform well in novel scenarios and environmental conditions it has never experienced. This is a big challenge of current machine learning systems that are not causal. In the future, the researchers want to explore the use of NCPs to build larger systems. Putting thousands or millions of networks together could enable them to tackle even more complicated tasks.

Recommended Stories

Linkedin-in Twitter Facebook-f Youtube Instagram
© 2021 OpenGov Asia – CIO Network Pte Ltd.
Send this to a friend