Making a fault-tolerant RL Octocopter

Building a Fault-Tolerant RL Octocopter: Direct Motor Control for Motor Failure Recovery

Karolina Dubiel outlines her technical plan for building a fault-tolerant octocopter drone that uses reinforcement learning (RL) to directly

Show HN: I made a 3D printed VTOL drone

Building a Quadruped Robot Dog for Mech Warfare Airsoft Competition

A maker documents their journey designing and building a quadruped robot dog from scratch for a 'Mech Warfare' airsoft battlebots competitio

AgenticRL Framework Uses AI Agents to Automate Reward Design for Drone Navigation, Achieving 91% Success Rate

The AgenticRL framework introduces AI agents that autonomously design reward functions and refine policies for deep reinforcement learning i

SkyJEPA: A Latent Dynamics Model for Zero-Shot Sim-to-Real Quadrotor Control

This paper introduces SkyJEPA, a Joint Embedding Predictive Architecture (JEPA) for learning long-horizon world models that enable zero-shot

SkyJEPA: A Latent Dynamics Model for Zero-Shot Sim-to-Real Quadrotor Control

This paper introduces SkyJEPA, a Joint Embedding Predictive Architecture (JEPA) for learning long-horizon world models that enable zero-shot

Building an Assembly Line for Origami Pigeons