Bullet Real-Time Physics Simulation

Bullet Real-Time Physics Simulation

Search
Skip to content
  • Blog
  • Forum
  • Github
  • PyBullet Quickstart Guide
  • Download
  • Documentation
  • Forum

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

March 17, 2020 admin

Robots can use meta-learning to quickly adapt from simulation to various real world conditions.

See paper at https://arxiv.org/abs/2003.01239

Post navigation

Previous PostLumote game using BulletNext PostLearning Agile Robotic Locomotion Skills by Imitating Animals

Last Topics Posts

  • m_collisionFlags !=btCollisionObject::CF_STATIC_OBJECT ?!?
    You should not set the linear velocity for static objects. Only dynamic and/or kinematic objects ...
    by goosesensor
    May 28, 2025 3:58 am
  • URDF importing correctly on one machine, incorrectly on another. Same code.
    Sprunki Game Have you tried compiling Bullet from source with debug flags on Machine B ...
    by otis
    May 2, 2025 7:25 am
  • I C A R U S - summer 2024 newsletter
    Stickman Hook Would you consider opening a public settings gallery or leaderboard where users upload ...
    by otis
    May 2, 2025 7:23 am
  • Soft body contact force
    For your case, I suggest adding a rigid sensor plate between the soft body and ...
    by otis
    March 17, 2025 10:18 am
  • Replicate ai generated animation back in pybullet.
    To replicate AI-generated animations in PyBullet smoothly, ditch time.sleep() and sync playback to p.stepSimulation() with ...
    by otis
    March 17, 2025 10:16 am

Home of Bullet and PyBullet: physics simulation for games, visual effects, robotics and reinforcement learning.

Recent Posts

  • Kubric: a scalable dataset generator
  • NeuralSim: Augmenting Differentiable Simulators with Neural Networks
  • PyBullet in a colab
  • Learning Agile Robotic Locomotion Skills by Imitating Animals
  • Assistive gym @ ICRA, 2020

Selected Video

 

 

(title expands video)

Proudly powered by WordPress