← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Vsim develops GPU-optimized virtual environment for rapid robot training

🔄 Updated 6d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Vsim's software trains robots in minutes, not days.
  • The system is optimized for GPUs, unlike older algorithms.
  • Robots can run 20,000 simulations per second while moving.
  • Founders previously worked on Nvidia's Isaac Sim.

Rapid Robot Training

Vsim, a British startup, has developed a virtual simulation environment that significantly reduces the time required to train robots. Their robot, Freddo, learned to walk, recognize, and grasp a bottle in minutes, a task that developers claim takes days with rival systems. This speed is attributed to Vsim's software, which allows tasks to be performed millions of times in simulation before being uploaded to hardware.

GPU Optimization

Founders Michelle Lu and Kier Storey, who previously worked on Nvidia's Isaac Sim, established Vsim in 2022 to build their own training system. They optimized their software to exploit the power of graphics processing units (GPUs), which are crucial for AI computations. Storey noted that traditional robotic simulation algorithms from the 1970s and 1980s are not well-suited for GPUs, leading to slower performance.

Real-time Simulation Capabilities

Vsim's software is efficient enough to run directly on a robot's hardware. This capability allows a robot like Freddo to perform tens of thousands of simulations while in motion. Storey explained that the robot can look approximately one second ahead, considering 20,000 different potential scenarios, which is vital for navigation in unstructured environments.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~26 min · 21 stories · Sep 23

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

British startup Vsim created a virtual simulation environment that trains robots in minutes, a process that typically takes days for rival systems. The software optimizes for GPUs, enabling robots to run thousands of simulations in real-time while operating.