Multi-Task Learning with Sequence-Conditioned Transporter Networks

Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches to solve such compositional tasks remains a challenge. In this work, we aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. First, we propose a new suite of benchmark specifically aimed at compositional tasks, MultiRavens, which allows defining custom task combinations through task modules that are inspired by industrial tasks and exemplify the difficulties in vision-based learning and planning methods. Second, we propose a vision-based end-to-end system architecture, Sequence-Conditioned Transporter Networks, which augments Goal-Conditioned Transporter Networks with sequence-conditioning and weighted sampling and can efficiently learn to solve multi-task long horizon problems. Our analysis suggests that not only the new framework significantly improves pick-and-place performance on novel 10 multi-task benchmark problems, but also the multi-task learning with weighted sampling can vastly improve learning and agent performances on individual tasks.

Authors

• Michael H. Lim
• Andy Zeng 0001
• Brian Ichter
• Maryam Bandari
• Erwin Coumans
• Claire J. Tomlin
• Stefan Schaal
• Aleksandra Faust

Keywords

• Automation
• Service robots
• Systems architecture
• Benchmark testing
• Multitasking
• Planning
• Task analysis
• Multi-task Learning
• Benchmark
• System Architecture
• Multiple Tasks
• Manipulation Tasks
• Individual Tasks
• Industrial Tasks
• Time Step
• Data Augmentation
• Workspace
• Attention Module
• Current Observations
• End-effector
• Objects In The Scene
• Balanced Sample
• Weighting Scheme
• Task Structure
• Fully Convolutional Network
• Curriculum Learning
• Expert Demonstrations
• Deformable Objects
• Motion Primitives
• Planning Horizon
• Multi-task Training
• Top-down View
• Convolution Module