Unverified50% confidenceEventExact time
A developer trained a quadrotor drone using Proximal Policy Optimization (PPO) to learn competitive racing on a 90-meter figure-eight gate course.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedThe simulation environment was built on Unreal Engine 5 combined with the JSBSim flight dynamics engine, with 96 drones training in parallel for a total of 100 million steps, all completed on a single laptop.66% similarUnverifiedAerospace engineers use Julia to optimize jet engine designs for faster numerical simulation iteration speeds.66% similarUnverifiedMorphi Robot employs a hybrid architecture combining a world model and VLA, capable of supporting complete long-horizon tasks lasting up to 15 minutes.58% similarUnverifiedA cute-style robot on display is equipped with an Intel Core processor, has 27 degrees of freedom, and can move fluidly in extremely small spaces while completing lightweight tasks.58% similarUnverified在人形机器人高速运动中，MPC需要在1-5毫秒内完成一次完整的优化求解循环57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996321API
curl https://kongchang.com/api/v1/knowledge/claims/996321MCP
get_claim(id=996321)