Teaching physical skills to humans requires one-on-one interaction betwe...
Vague objectives in many real-life scenarios pose long-standing challeng...
Inverse reinforcement learning (IRL) algorithms often rely on (forward)
...
In the autonomous driving system, trajectory prediction plays a vital ro...
Natural language provides a natural interface for human communication, y...
Identifying internal parameters for planning is crucial to maximizing th...
Knowledge and skills can transfer from human teachers to human students....
Deformable Object Manipulation (DOM) is of significant importance to bot...
Grounding spatial relations in natural language for object placing could...
Uncertainty on human behaviors poses a significant challenge to autonomo...
Noisy sensing, imperfect control, and environment changes are defining
c...
Inverse reinforcement learning (IRL) seeks to infer a cost function that...
An inverse reinforcement learning (IRL) agent learns to act intelligentl...
How can a robot navigate successfully in a rich and diverse environment,...
This paper presents INVIGORATE, a robot system that interacts with human...
This paper presents Particle-based Object Manipulation (Prompt), a new
a...
Simultaneous localization and mapping (SLAM) remains challenging for a n...
Manipulating deformable objects, such as cloth and ropes, is a long-stan...
Imagine an autonomous robot vehicle driving in dense, possibly unregulat...
Autonomous driving in an unregulated urban crowd is an outstanding chall...
When robots operate in the real-world, they need to handle uncertainties...
Deep model-based reinforcement learning (MBRL) has achieved great
sample...
It has been arduous to assess the progress of a policy learning algorith...
Deep reinforcement learning is successful in decision making for
sophist...
Autonomous driving in an unregulated urban crowd is an outstanding chall...
In this paper, we present results from a human-subject study designed to...
Recurrent neural networks (RNNs) have been extraordinarily successful fo...
Autonomous driving in a crowded environment, e.g., a busy traffic
inters...
This paper introduces the Differentiable Algorithm Network (DAN), a
comp...
Robot understanding of human intentions is essential for fluid human-rob...
We propose to take a novel approach to robot system design where each
bu...
Trust is crucial in shaping human interactions with one another and with...
This paper presents INGRESS, a robot system that follows human natural
l...
This paper presents a planning system for autonomous driving among many
...
Driving among a dense crowd of pedestrians is a major challenge for
auto...
Particle filtering is a powerful method for sequential state estimation ...
Particle filters sequentially approximate posterior distributions by sam...
Planning under uncertainty is critical for robust robot performance in
u...
Trust is essential for human-robot collaboration and user adoption of
au...
How can a delivery robot navigate reliably to a destination in a new off...
The human language is one of the most natural interfaces for humans to
i...
This paper introduces the QMDP-net, a neural network architecture for
pl...
Scarce data is a major challenge to scaling robot learning to truly comp...
The partially observable Markov decision process (POMDP) provides a
prin...
The partially observable Markov decision process (POMDP) provides a
prin...
Bayesian reinforcement learning (BRL) encodes prior knowledge of the wor...