HomeRobot (noun): An affordable compliant robot that navigates homes and...
Manipulating objects without grasping them is an essential component of ...
In order for robots to follow open-ended instructions like "go open the ...
We investigate how to build and train spatial representations for robot
...
Images are a convenient way to specify which particular object instance ...
Multi-object rearrangement is a crucial skill for service robots, and
co...
Robots operating in human environments must be able to rearrange objects...
We propose CLIP-Fields, an implicit scene model that can be trained with...
We introduce a new simulation benchmark "HandoverSim" for human-to-robot...
When humans design cost or goal specifications for robots, they often pr...
Human-robot handover is a fundamental yet challenging task in human-robo...
Rearrangement tasks have been identified as a crucial challenge for
inte...
Language model (LM) pre-training has proven useful for a wide variety of...
Accurate object rearrangement from vision is a crucial problem for a wid...
We have recently introduced a system that automatically generates roboti...
Robots need to be able to learn concepts from their users in order to ad...
Geometric organization of objects into semantically meaningful arrangeme...
Sequential manipulation tasks require a robot to perceive the state of a...
Human environments contain numerous objects configured in a variety of
a...
Seemingly simple natural language requests to a robot are generally
unde...
Natural language provides an accessible and expressive interface to spec...
Robots will be expected to manipulate a wide variety of objects in compl...
Automated planning enables robots to find plans to achieve complex,
long...
In many applications, including logistics and manufacturing, robot
manip...
Human-robot object handovers have been an actively studied area of robot...
Zero-shot execution of unseen robotic tasks is an important problem in
r...
Transfer of objects between humans and robots is a critical capability f...
While robots can learn models to solve many manipulation tasks from raw
...
Grasping in cluttered environments is a fundamental but challenging robo...
We address goal-based imitation learning, where the aim is to output the...
To solve multi-step manipulation tasks in the real world, an autonomous ...
Widespread adoption of self-driving cars will depend not only on their s...
Effective human-robot collaboration requires informed anticipation. The ...
In order to learn effectively, robots must be able to extract the intang...
It is difficult to create robust, reusable, and reactive behaviors for r...
High-level human instructions often correspond to behaviors with multipl...
How can we enable users to create effective, perception-driven task plan...
We propose HyperTrees for the low cost automatic design of multiple-inpu...
Prospection, the act of predicting the consequences of many possible fut...
Fast, collision-free motion through unknown environments remains a
chall...
Prospection is an important part of how humans come up with new task pla...
Accurate knowledge of object poses is crucial to successful robotic
mani...