Robot dog learns to hook and drag IKEA chairs, succeeding in 40/58 trials
ChongZzZhang · x · 2026-09-02
- Core Achievement: The ALMA quadruped robot learned to transport non-prehensile objects like IKEA chairs using a contact-guided exploration strategy. It succeeded in 40 out of 58 real-world trials on 4 unseen objects.
- Technical Method: Uses a Multi-Critic Reinforcement Learning (RL) framework. A dedicated exploration critic rewards finding contact early in training. Once interaction points are reliably discovered, this objective fades, and the policy focuses on moving the object to the goal.
- Behavior: The robot uses its arm to discover useful contact points, then pushes, pulls, and hooks bulky objects while coordinating its whole body. It can even reposition and retry with a larger swing if a hook slips.
- Use Cases: Non-prehensile manipulation is versatile for heavy or bulky objects. The paper also demonstrates box pushing and dishwasher opening tasks.
Paper Link
More from Embodied
- China’s real robot revolution is not about humanoids, but industrial application — zijing_wu · 2026-09-02
- Gemini-powered Spatial OS turns 8 photos into 3D digital twins — AI_Andrew · 2026-09-02
- Robot Training Video: Squire Model Shows New Skills — MocaPoka · 2026-09-02
- Open-source humanoid robot Asimov 1 starts shipping to 20+ countries — MikeBirdTech · 2026-09-02
- Physical AI Deep Dive: From Static Programming to Imitation Learning and Edge Compute — ShawnHymel · 2026-09-02
- Arduino's Zephyr-based core officially leaves beta as mbedOS cores enter deprecation — JeremyCMorgan · 2026-09-02