Category: Blog

A USC RASC blog post by Jesse Zhang and Abrar Anwar. Introduction In The Automatic Motorist, a robot chauffeur takes a newlywed couple from Earth’s dirt roads to Saturn’s rocky rings—all while evading police. This 1911 (!) short film depicted a generalist robot before the word “robot” even existed. Until recently, robotics research focused on … Continue reading From Generalists to Specialists: A Case for Real-World RL in Robot Manipulation

The widespread success of foundation models like ChatGPT, Gemini, Deepseek, and Claude demonstrates the effectiveness of scaling data collection to address many vision and language tasks. Robotics has also seen benefits from learning from large amounts of high-quality data, but robots are still not reliably performing many of the tasks that people do every day … Continue reading Capturing the Data That Users Naturally Emit

Imagine deploying a robot in a new environment. While it has been pre-trained in a factory, its performance is far from perfect when faced with real-world variability. Whether it’s a warehouse robot handling unexpected objects or a household assistant adapting to a cluttered kitchen, fine-tuning is often necessary to bridge the gap between training and … Continue reading MILE: Model-based Intervention Learning

Why make a walker that can trip people? In rehabilitation there has been an increase in the use of robotics for research purposes. This often takes the form of software written for commercial robots. The design of hardware systems for rehabilitation in robotics provides another avenue for studying human behavior. For assistive device users, especially, … Continue reading FALL-E: A Robotic Walker to Learn About Balance

By Abrar Anwar Robots are increasingly expected to perceive and interact with their environments over extended periods. Robots are deployed for hours, if not days, at a time and they incidentally perceive different objects, events, and locations. For robots to understand and respond to questions that require complex multi-step reasoning in scenarios where the robot has … Continue reading ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation

By Ishika Singh Everyday household tasks require both common sense understanding of the world and situated knowledge about the current environment. To create a task plan for “Make dinner” an agent needs common sense: object affordances, such as the stove can be used to make food; logical sequences of actions, such as the oven must be preheated … Continue reading Language Models meet Classical Planners to make smarter Robot Task Plans

Quality Diversity algorithms identify many diverse solutions to solve problems rather than a single best option. Researchers developed pyribs to facilitate development of research projects that use Quality Diversity. Continue reading pyribs: Accelerating Quality Diversity Research

Large language models can help our robots adapt to new tasks and situations by enabling better pre-training and by guiding them in unfamiliar settings. Continue reading LLMs can help robots learn new tasks in unfamiliar places