Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss.
William PrewToby P. BreckonMagnus BordewichUlrik R. BeierholmPublished in: CoRR (2020)
Keyphrases
- multi task learning
- monocular images
- multi task
- gaussian processes
- human body
- pose estimation
- vision system
- learning tasks
- transfer learning
- learning problems
- high order
- learning models
- human pose
- theoretical analysis
- depth estimation
- learning algorithm
- data sets
- visual features
- text classification
- image classification
- object recognition