In this work we present CppFlow - a novel and performant planner for the...
Multi-robot collision-free and deadlock-free navigation in cluttered
env...
Complex manipulation tasks often require robots with complementary
capab...
Collision-free navigation in cluttered environments with static and dyna...
Reinforcement learning (RL) has shown promise in creating robust policie...
Granular materials are of critical interest to many robotic tasks in
pla...
Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has
...
Robotic assembly is a longstanding challenge, requiring contact-rich
int...
We are motivated by quantile estimation of algae concentration in lakes ...
When robots are deployed in the field for environmental monitoring they
...
Quantiles of a natural phenomena can provide scientists with an importan...
Collision-free mobile robot navigation is an important problem for many
...
Household robots operate in the same space for years. Such robots
increm...
In active source seeking, a robot takes repeated measurements in order t...
We introduce OPEND, a benchmark for learning how to use a hand to open
c...
Household environments are visually diverse. Embodied agents performing
...
Neural control of memory-constrained, agile robots requires small, yet h...
We propose a multimodal (vision-and-language) benchmark for cooperative ...
We consider the setting where a team of robots is tasked with tracking
m...
We present a novel Learning from Demonstration (LfD) method, Deformable
...
Physically rearranging objects is an important capability for embodied
a...
Multi-robot SLAM systems in GPS-denied environments require loop closure...
Language-guided Embodied AI benchmarks requiring an agent to navigate an...
When is heterogeneity in the composition of an autonomous robotic team
b...
We introduce a novel privacy-preserving methodology for performing Visua...
Scientists interested in studying natural phenomena often take physical
...
Learning complex manipulation tasks in realistic, obstructed environment...
Learning-based methods for training embodied agents typically require a ...
In order to be effective general purpose machines in real world environm...
Robustness is key to engineering, automation, and science as a whole.
Ho...
We investigate improving Monte Carlo Tree Search based solvers for Parti...
To accurately reproduce measurements from the real world, simulators nee...
We consider a scenario where a team of robots with heterogeneous sensors...
Robots are used for collecting samples from natural environments to crea...
Differentiable simulators provide an avenue for closing the sim-to-real ...
Deep reinforcement learning (RL) agents are able to learn contact-rich
m...
Constrained robot motion planning is a widely used technique to solve co...
We propose a framework for resilience in a networked heterogeneous
multi...
We present a differentiable simulation architecture for articulated
rigi...
Robots need to be able to adapt to unexpected changes in the environment...
Representing the environment is a fundamental task in enabling robots to...
Motion planning with constraints is an important part of many real-world...
We address the problem of planning robot motions in constrained configur...
Robot control problems are often structured with a policy function that ...
One of the great promises of robot learning systems is that they will be...
We address the problem of maintaining resource availability in a network...
Public cameras often have limited metadata describing their attributes. ...
Planning smooth and energy-efficient motions for wheeled mobile robots i...
A key ingredient to achieving intelligent behavior is physical understan...
Light Detection and Ranging (LIDAR) sensors play an important role in th...