Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Train an ACT Policy for the SO-101 Robot with LeRobot

Trelis Research via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to train an Action Chunking with Transformers (ACT) policy for the SO-101 robot using the LeRobot library in this comprehensive tutorial. Begin by setting up the development environment through cloning and installing LeRobot libraries, then progress through connecting and configuring robots, calibrating motors and arms, and establishing teleoperation capabilities. Master PID controller calibration techniques before diving into data recording and management processes. Explore the ACT model training workflow, including advanced style settings and KL weight configuration, with detailed guidance for running training on both Mac/CPU and GPU environments. Navigate through validation setup, output directory configuration, and troubleshooting common issues encountered during CUDA-based training. Monitor training progress effectively while learning to calculate training steps and epochs, analyze training and validation loss patterns, and evaluate model performance through replay and evaluation of training examples. Address challenges related to generalization and data requirements, implement image augmentations and jitter techniques, determine optimal rollout steps, and apply ensembling predictions for smoother robot trajectories, concluding with practical next steps for continued development.

Syllabus

00:00 Introduction to Training the SO-101 Robot with ACT
00:21 Overview of the Video Series
01:16 Scripts and Repo Access: Trelis.com/ADVANCED-robotics
01:57 Cloning and Installing LeRobot Libraries
06:07 Connecting and Configuring the Robots
08:53 Calibrating the Motors and Arms
12:33 Teleoperation Setup
18:04 PID Controller Calibration
27:10 Recording and Managing Data
39:05 Training the ACT Model
44:33 Style settings and KL Weight ADVANCED
49:06 Running Training on a Mac or cpu
50:54 Setting Up Validation and Output Directories
53:44 Running Training on Mac and Handling Issues
55:31 Monitoring Training Progress
57:25 Calculating Training S teps and Epochs
58:28 Analyzing Training and Validation Loss
01:04:02 Setting Up Training on GPU
01:08:19 Connecting to Remote Host and Cloning Repo
01:12:48 Running Training on CUDA
01:14:48 Handling Issues Running on CUDA
01:23:28 Inspecting Results after Running on CUDA
01:27:04 Evaluating Model Performance
01:28:37 Replay and Evaluation of Training Examples
01:35:21 Challenges with Generalization and Data Requirements
01:36:28 Using Image Augmentations and Jitter
01:37:08 Deciding Number of Rollout Steps
01:40:06 Ensembling Predictions for Smoother Trajectories
01:43:43 Conclusion and Next Steps

Taught by

Trelis Research

Reviews

Start your review of Train an ACT Policy for the SO-101 Robot with LeRobot

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.