Goto

Collaborating Authors

 shaheen


A Heterogeneous RISC-V based SoC for Secure Nano-UAV Navigation

arXiv.org Artificial Intelligence

The rapid advancement of energy-efficient parallel ultra-low-power (ULP) ucontrollers units (MCUs) is enabling the development of autonomous nano-sized unmanned aerial vehicles (nano-UAVs). These sub-10cm drones represent the next generation of unobtrusive robotic helpers and ubiquitous smart sensors. However, nano-UAVs face significant power and payload constraints while requiring advanced computing capabilities akin to standard drones, including real-time Machine Learning (ML) performance and the safe co-existence of general-purpose and real-time OSs. Although some advanced parallel ULP MCUs offer the necessary ML computing capabilities within the prescribed power limits, they rely on small main memories (<1MB) and ucontroller-class CPUs with no virtualization or security features, and hence only support simple bare-metal runtimes. In this work, we present Shaheen, a 9mm2 200mW SoC implemented in 22nm FDX technology. Differently from state-of-the-art MCUs, Shaheen integrates a Linux-capable RV64 core, compliant with the v1.0 ratified Hypervisor extension and equipped with timing channel protection, along with a low-cost and low-power memory controller exposing up to 512MB of off-chip low-cost low-power HyperRAM directly to the CPU. At the same time, it integrates a fully programmable energy- and area-efficient multi-core cluster of RV32 cores optimized for general-purpose DSP as well as reduced- and mixed-precision ML. To the best of the authors' knowledge, it is the first silicon prototype of a ULP SoC coupling the RV64 and RV32 cores in a heterogeneous host+accelerator architecture fully based on the RISC-V ISA. We demonstrate the capabilities of the proposed SoC on a wide range of benchmarks relevant to nano-UAV applications. The cluster can deliver up to 90GOp/s and up to 1.8TOp/s/W on 2-bit integer kernels and up to 7.9GFLOp/s and up to 150GFLOp/s/W on 16-bit FP kernels.


Taliban investigating US 'claim' of killing al-Qaeda chief

Al Jazeera

The Taliban says it is investigating a "claim" by the United States that it killed al-Qaeda leader Ayman al-Zawahiri in a drone attack in Kabul, says a Taliban official, indicating the group's leadership was not aware of his presence there. The US said it killed al-Zawahiri with a missile fired from a drone while he stood on a balcony at his Kabul hiding place on Sunday. US officials said the killing was the biggest blow to the armed group since its founder, Osama bin Laden was shot dead more than 10 years ago. "The government and the leadership wasn't aware of what is being claimed, nor any trace there," Suhail Shaheen, the designated Taliban representative to the United Nations, who is based in Doha, told journalists in a message. "Investigation is under way now to find out about the veracity of the claim," he said, adding that the results of the investigation would be shared publicly.


City of the future is closer, calmer than you think

USATODAY - Tech Top Stories

A USA TODAY motion graphic showing what a city of the future may look like. Cities of the future could be a haven of largely driverless efficiency and tranquility, but there are many potential potholes on the road to this vision. SAN FRANCISCO – The city of the future has had countless fantasy blueprints, from The Jetsons' pleasant hive of automated efficiency to Blade Runner's dystopian tangle of urban chaos. But the reality is the city of future is closer than you think, as tech companies and automakers floor the pedal on projects ranging from cars that drive themselves to apps that aggregate transportation options. Conversations with mobility experts here and abroad paint a picture of an urban revolution that is already underway in a patchwork of cities from Seattle to Stockholm.


Can Ride Apps Really Solve America's Traffic Woes?

TIME - Tech

For 20 years she's been studying what transport gurus call shared mobility, dissecting factors that make it successful, like shorter wait times. Though you might think choosing how to get to work is simple, Shaheen will tell you that especially in urban areas, there are countless factors in play, from the time of day you're on the move to whether you own a smartphone. And more than any of the tech executives giving speeches lately about how we all should rethink our relationship to our cars, she knows just how revolutionary that could be. Walking the halls of one of the nation's oldest departments dedicated to transportation research, at the University of California, Berkeley, the engineering professor wonders how our lives would have turned out if the Model T had been marketed as something to be shared, not owned home by home. Would our vehicles still be idle an estimated 95% of the time?