DISeR: Designing Imaging Systems with Reinforcement Learning
Imaging systems consist of cameras to encode visual information about the world and
perception models to interpret this encoding. Cameras contain (1) illumination sources,(2) …
perception models to interpret this encoding. Cameras contain (1) illumination sources,(2) …
A Review of Differentiable Simulators
Differentiable simulators continue to push the state of the art across a range of domains
including computational physics, robotics, and machine learning. Their main value is the …
including computational physics, robotics, and machine learning. Their main value is the …
Co-design optimisation of morphing topology and control of winged drones
The design and control of winged aircraft and drones is an iterative process aimed at
identifying a compromise of mission-specific costs and constraints. When agility is required …
identifying a compromise of mission-specific costs and constraints. When agility is required …
RoboMorph: Evolving Robot Morphology using Large Language Models
We introduce RoboMorph, an automated approach for generating and optimizing modular
robot designs using large language models (LLMs) and evolutionary algorithms. In this …
robot designs using large language models (LLMs) and evolutionary algorithms. In this …
Robot Graph Grammars: Towards Custom Robots for Every Task
A Zhao - 2024 - dspace.mit.edu
As robots find broader applications outside factory floors, they face an increasing number of
challenges. For example, they must accommodate rugged terrain, limited battery capacity …
challenges. For example, they must accommodate rugged terrain, limited battery capacity …
[PDF][PDF] Co-Designing Manipulation Systems Using Task-Relevant Constraints
A robotic system's hardware and control policy must be co-optimized to ensure they
complement each other to interact robustly with the environment. However, this combined …
complement each other to interact robustly with the environment. However, this combined …