Intel Loihi 2ニューロモーフィックハードウェアによる自律強化学習ロボット制御
Autonomous Reinforcement Learning Robot Control with Intel's Loihi 2 Neuromorphic Hardware
シミュレーションで訓練した強化学習方策をスパイキングニューラルネットワークに変換し、Intel Loihi 2上でAstrobeeロボットの制御を実現した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kenneth Stewart, Roxana Leontie, Samantha Chapin, Joe Hays, Sumit Bam Shrestha, Carl Glen Henshaw
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
We present an end-to-end pipeline for deploying reinforcement learning (RL) trained Artificial Neural Networks (ANNs) on neuromorphic hardware by converting them into spiking Sigma-Delta Neural Networks (SDNNs). We demonstrate that an ANN policy trained entirely in simulation can be transformed into an SDNN compatible with Intel's Loihi 2 architecture, enabling low-latency and energy-efficient inference. As a test case, we use an RL policy for controlling the Astrobee free-flying robot, similar to a previously hardware in space-validated controller. The policy, trained with Rectified Linear Units (ReLUs), is converted to an SDNN and deployed on Intel's Loihi 2, then evaluated in NVIDIA's Omniverse Isaac Lab simulation environment for closed-loop control of Astrobee's motion. We compare execution performance between GPU and Loihi 2. The results highlight the feasibility of using neuromorphic platforms for robotic control and establish a pathway toward energy-efficient, real-time neuromorphic computation in future space and terrestrial robotics applications.
