Search Results for author: Andreea Bobu

Found 16 papers, 3 papers with code

Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation

no code implementations12 Jul 2023 Andi Peng, Aviv Netanyahu, Mark Ho, Tianmin Shu, Andreea Bobu, Julie Shah, Pulkit Agrawal

Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments.

Continuous Control counterfactual +1

Aligning Robot and Human Representations

no code implementations3 Feb 2023 Andreea Bobu, Andi Peng, Pulkit Agrawal, Julie Shah, Anca D. Dragan

To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior.

Imitation Learning Representation Learning

SIRL: Similarity-based Implicit Representation Learning

no code implementations2 Jan 2023 Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan

This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not.

Contrastive Learning Data Augmentation +1

Time-Efficient Reward Learning via Visually Assisted Cluster Ranking

no code implementations30 Nov 2022 David Zhang, Micah Carroll, Andreea Bobu, Anca Dragan

One of the most successful paradigms for reward learning uses human feedback in the form of comparisons.

Dimensionality Reduction

Aligning Robot Representations with Humans

no code implementations15 May 2022 Andreea Bobu, Andi Peng

As robots are increasingly deployed in real-world scenarios, a key question is how to best transfer knowledge learned in one environment to another, where shifting constraints and human preferences render adaptation challenging.

Teaching Robots to Span the Space of Functional Expressive Motion

no code implementations4 Mar 2022 Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan

As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot can respond emotively to user-generated natural language by mapping it to a target VAD.

Inducing Structure in Reward Learning by Learning Features

1 code implementation18 Jan 2022 Andreea Bobu, Marius Wiggert, Claire Tomlin, Anca D. Dragan

To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously.

Learning Perceptual Concepts by Bootstrapping from Human Queries

no code implementations9 Nov 2021 Andreea Bobu, Chris Paxton, Wei Yang, Balakumar Sundaralingam, Yu-Wei Chao, Maya Cakmak, Dieter Fox

Second, we treat this low-dimensional concept as an automatic labeler to synthesize a large-scale high-dimensional data set with the simulator.

Motion Planning Object

Situational Confidence Assistance for Lifelong Shared Autonomy

no code implementations14 Apr 2021 Matthew Zurek, Andreea Bobu, Daniel S. Brown, Anca D. Dragan

Shared autonomy enables robots to infer user intent and assist in accomplishing it.

Dynamically Switching Human Prediction Models for Efficient Planning

no code implementations13 Mar 2021 Arjun Sripathy, Andreea Bobu, Daniel S. Brown, Anca D. Dragan

As environments involving both robots and humans become increasingly common, so does the need to account for people during planning.

Feature Expansive Reward Learning: Rethinking Human Input

1 code implementation23 Jun 2020 Andreea Bobu, Marius Wiggert, Claire Tomlin, Anca D. Dragan

When the correction cannot be explained by these features, recent work in deep Inverse Reinforcement Learning (IRL) suggests that the robot could ask for task demonstrations and recover a reward defined over the raw state space.

Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections

no code implementations3 Feb 2020 Andreea Bobu, Andrea Bajcsy, Jaime F. Fisac, Sampada Deglurkar, Anca D. Dragan

Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives.

LESS is More: Rethinking Probabilistic Models of Human Behavior

no code implementations13 Jan 2020 Andreea Bobu, Dexter R. R. Scobee, Jaime F. Fisac, S. Shankar Sastry, Anca D. Dragan

A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward function and choose trajectories in proportion to their exponentiated reward.


Learning under Misspecified Objective Spaces

1 code implementation11 Oct 2018 Andreea Bobu, Andrea Bajcsy, Jaime F. Fisac, Anca D. Dragan

Learning robot objective functions from human input has become increasingly important, but state-of-the-art techniques assume that the human's desired objective lies within the robot's hypothesis space.

Cannot find the paper you are looking for? You can Submit a new open access paper.