generation service
Dynamic Open Vocabulary Enhanced Safe-landing with Intelligence (DOVESEI)
Bong, Haechan Mark, Zhang, Rongge, de Azambuja, Ricardo, Beltrame, Giovanni
This work targets what we consider to be the foundational step for urban airborne robots, a safe landing. Our attention is directed toward what we deem the most crucial aspect of the safe landing perception stack: segmentation. We present a streamlined reactive UAV system that employs visual servoing by harnessing the capabilities of open vocabulary image segmentation. This approach can adapt to various scenarios with minimal adjustments, bypassing the necessity for extensive data accumulation for refining internal models, thanks to its open vocabulary methodology. Given the limitations imposed by local authorities, our primary focus centers on operations originating from altitudes of 100 meters. This choice is deliberate, as numerous preceding works have dealt with altitudes up to 30 meters, aligning with the capabilities of small stereo cameras. Consequently, we leave the remaining 20m to be navigated using conventional 3D path planning methods. Utilizing monocular cameras and image segmentation, our findings demonstrate the system's capability to successfully execute landing maneuvers at altitudes as low as 20 meters. However, this approach is vulnerable to intermittent and occasionally abrupt fluctuations in the segmentation between frames in a video stream. To address this challenge, we enhance the image segmentation output by introducing what we call a dynamic focus: a masking mechanism that self adjusts according to the current landing stage. This dynamic focus guides the control system to avoid regions beyond the drone's safety radius projected onto the ground, thus mitigating the problems with fluctuations. Through the implementation of this supplementary layer, our experiments have reached improvements in the landing success rate of almost tenfold when compared to global segmentation. All the source code is open source and available online (github.com/MISTLab/DOVESEI).
- Europe > Switzerland > Zürich > Zürich (0.14)
- North America > Canada > Quebec > Montreal (0.05)
- North America > United States > Illinois > Cook County > Chicago (0.04)
- (2 more...)
Competition Briefing Edinburgh - Next Generation Services: Enabling Data
Innovate UK, as part of UK Research and Innovation, will invest up to £3.5 million to develop data access methods to enable the application of artificial intelligence (AI) and data technologies in the accountancy, insurance and legal services sector. In this competition, individuals can apply, on behalf of their organisation, to take part in a 3-day residential Innovation Lab. The selected participants will work together to develop consortia and project proposals to enable a more accessible data environment within the accountancy, insurance and legal sectors. After the Innovation Lab, the developed project collaborations will have 3 weeks to finalise their proposals before submitting them for assessment. Competition briefing events will be held in London, Manchester and Edinburgh.
Introducing Wealthfront 3.0
When we launched Wealthfront in December 2011, the idea behind our first generation service was simple: take the best practices of investment management like diversification, rebalancing, dividend reinvestment and tax-loss harvesting, and automate them so investors could get these benefits without the high fees and high minimums of the traditional industry. The advent of low-cost ETFs and the relentlessly improving economics of consumer software made Wealthfront 1.0 possible. In December 2013, we launched Wealthfront 2.0. Our second generation service built a series of high value-added services that previously were only available to the wealthy, and layered them on top of our basic service. These innovative services include our Direct Indexing Platform, Single-Stock Diversification Service, and Automated Tax-Minimized Brokerage Transfers.
- Banking & Finance > Financial Services (0.75)
- Banking & Finance > Trading (0.51)
Introducing the new Wealthfront Dashboard
When we launched Wealthfront in December 2011, the idea behind our first generation service was simple: take the best practices of investment management like diversification, rebalancing, dividend reinvestment and tax-loss harvesting, and automate them so investors could get these benefits without the high fees and high minimums of the traditional industry. The advent of low-cost ETFs and the relentlessly improving economics of consumer software made Wealthfront 1.0 possible. In December 2013, we launched Wealthfront 2.0. Our second generation service built a series of high value-added services that previously were only available to the wealthy, and layered them on top of our basic service. These innovative services include our Direct Indexing Platform, Single-Stock Diversification Service, and Automated Tax-Minimized Brokerage Transfers.
- Banking & Finance > Financial Services (0.76)
- Banking & Finance > Trading (0.51)