Page 2 of 3 for Robotics Posts - Page 2

Back to the Future: Planning-Aware Trajectory Forecasting for Autonomous Driving

Recent advances in deep generative modeling have brought forth a paradigm shift in trajectory forecasting. In this blog post, we provide an overview of existing work, highlight new opportunities, and present our latest work on developing methods that are cognizant of their downstream use cases.

Making Sense of Vision and Touch: Multimodal Representations for Contact-Rich Tasks

Michelle A. Lee

Contact-rich manipulation tasks in unstructured environments often require both tactile and visual feedback. In this blog post, we introduce how to use self-supervision to learn a compact and multimodal representation of vision and touch.

Leveraging Compositionality for One-Shot Imitation Learning

De-An Huang, Danfei Xu

We introduce a class of algorithms that solve long-horizon one-shot imitation learning by leveraging compositional priors.

Sequential Problem Solving by Hierarchical Planning in Latent Spaces

Kuan Fang

We propose a hierarchical planning algorithm in learned latent spaces. Our method uses deep generative models to prioritize promising actions for sampling-based planning.

When Humans Aren’t Optimal: Robots that Collaborate with Risk-Aware Humans

Minae Kwon and Dylan Losey

To create human-like robots, we need to understand how humans behave. We present a modeling approach enables robots to anticipate that humans will make suboptimal choices when risk and uncertainty are involved.

RoboNet: A Dataset for Large-Scale Multi-Robot Learning

Sudeep Dasari

We introduce RoboNet, an open database for sharing robotic experience, and study how this data can be used to learn generalizable models for vision-based robotic manipulation. We find that pre-training on RoboNet enables faster learning in new environments compared to learning from scratch.

Controlling Assistive Robots with Learned Latent Actions

Dylan Losey

We want to make it easier for humans to teleoperate dexterous robots. We present a learning approach that embeds high-dimensional robot actions into an intuitive, human-controllable, and low-dimensional latent space.

RoboTurk: Human Reasoning and Dexterity for Large-Scale Dataset Creation

Ajay Mandlekar

We built a system that enables collecting large-scale robot manipulation datasets with human supervision and used it to collect the largest robot dataset ever collected via teleoperation.

Learning from My Partner’s Actions: Roles in Decentralized Robot Teams

Dylan Losey

When groups robots work together, their actions communicate valuable information. We introduce a collaborative learning and control strategy that enables robots to harness the information contained within their partner's actions.

AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers

Andrey Kurenkov and Ajay Mandlekar

Presenting AC-Teach, a unifying approach to leverage advice from an ensemble of sub-optimal teachers in order to accelerate the learning process of actor-critic reinforcement learning agents.