Media Summary: What are the properties of a model that translates image-based Many recent foundational model papers use The so-called "visuospatial skills" allow people to

Robot Learning Visual Goal Condition - Detailed Analysis & Overview

What are the properties of a model that translates image-based Many recent foundational model papers use The so-called "visuospatial skills" allow people to This video shows the result of our work on For more information about Stanford's online Artificial Intelligence programs visit: This lecture covers: 1. This AI detection using Yolo V3 is used in

Members of the Agility team talk about perception and how it enables Digit to work in real-world environments, as well as our ...

Photo Gallery

Robot Learning: Visual Goal-Condition Reinforcement Learning
Robot Learning: Goal-Condition Panning
Interactive Robot Learning of Visuospatial Skills
ViNG: Learning Open-World Navigation with Visual Goals (ICRA 2021 Summary Video)
Visual Reinforcement Learning with Imagined Goals
Efficient Vision-based Navigation - Learning about the Influence of Motion Blur
Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 17: Robot Learning
RoboCup Middle Size League : Detection of goal, robots and ball using deep learning.
Lund University project in intelligent robotics - Robot Learning through Goal Emulation
Robotic learning of a navigation task including a waiting period at the goal location
Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation
Explained: How Humanoid Robots Perceive the World
View Detailed Profile
Robot Learning: Visual Goal-Condition Reinforcement Learning

Robot Learning: Visual Goal-Condition Reinforcement Learning

What are the properties of a model that translates image-based

Robot Learning: Goal-Condition Panning

Robot Learning: Goal-Condition Panning

Many recent foundational model papers use

Interactive Robot Learning of Visuospatial Skills

Interactive Robot Learning of Visuospatial Skills

The so-called "visuospatial skills" allow people to

ViNG: Learning Open-World Navigation with Visual Goals (ICRA 2021 Summary Video)

ViNG: Learning Open-World Navigation with Visual Goals (ICRA 2021 Summary Video)

We present

Visual Reinforcement Learning with Imagined Goals

Visual Reinforcement Learning with Imagined Goals

I presented https://arxiv.org/pdf/1807.04742.pdf.

Efficient Vision-based Navigation - Learning about the Influence of Motion Blur

Efficient Vision-based Navigation - Learning about the Influence of Motion Blur

This video shows the result of our work on

Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 17: Robot Learning

Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 17: Robot Learning

For more information about Stanford's online Artificial Intelligence programs visit: https://stanford.io/ai This lecture covers: 1.

RoboCup Middle Size League : Detection of goal, robots and ball using deep learning.

RoboCup Middle Size League : Detection of goal, robots and ball using deep learning.

This AI detection using Yolo V3 is used in

Lund University project in intelligent robotics - Robot Learning through Goal Emulation

Lund University project in intelligent robotics - Robot Learning through Goal Emulation

Learning

Robotic learning of a navigation task including a waiting period at the goal location

Robotic learning of a navigation task including a waiting period at the goal location

A Robulab-10 mobile

Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation

Skill Fusion in Hybrid Robotic Framework for Visual Object Goal Navigation

... as object

Explained: How Humanoid Robots Perceive the World

Explained: How Humanoid Robots Perceive the World

Members of the Agility team talk about perception and how it enables Digit to work in real-world environments, as well as our ...

Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives

Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives

Goal