Latest

• Optimizing at All Scales: Edge (Non)linear Model Predictive Control from MCUs to GPUs
• Invited: The Magnificent Seven Challenges and Opportunities in Domain-Specific Accelerator Design for Autonomous Systems
• Parallel Optimization for Robotics: An Undergraduate Introduction to GPU Parallel Programming and Numerical Optimization Research
• TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers
• MPCGPU: Real-Time Nonlinear Model Predictive Control through Preconditioned Conjugate Gradient on the GPU
• Symmetric Stair Preconditioning of Linear Systems for Parallel Trajectory Optimization
• Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning
• RobotPerf: An Open-Source, Vendor-Agnostic, Benchmarking Suite for Evaluating Robotics Computing System Performance
• Code Generation for Conic Model-Predictive Control on Microcontrollers with TinyMPC
• TinyML4D: Scaling Embedded Machine Learning Education in the Developing World
• Underrepresentation of Women in Robotics Research
• Materiality and Risk in the Age of Pervasive AI Sensors
• AI in the Developing World: How ‘Tiny Machine Learning’ can have a Big Impact
• Can Large Language Models Reduce the Barriers to Entry for High School Robotics?
• Tiny Robot Learning: Expanding Access to Edge ML as a Step Toward Accessible Robotics
• Datasheets for Machine Learning Sensors
• RoboShape: Using Topology Patterns to Scalably and Flexibly Deploy Accelerators Across Robots
• Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
• Bridging the Digital Divide: the Promising Impact of TinyML for Developing Countries
• Machine Learning Sensors: A Design Paradigm for the Future of Intelligent Sensors
• Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers
• Stop Reinventing the Wheel! Promoting Community Software in Computing Education
• Leveraging Community Software in CS Education to Avoid Reinventing the Wheel
• RobotCore: An Open Architecture for Hardware Acceleration in ROS 2
• Closing the Sim-to-Real Gap for Ultra-Low-Cost, Resource-Constrained, Quadruped Robot Platforms
• Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots
• Machine Learning Sensors
• TinyML: Applied AI for Development
• GPU Acceleration for Real-time, Whole-body, Nonlinear Model Predictive Control
• TinyMLedu: The Tiny Machine Learning Open Education Initiative
• GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients
• Widening Access to Applied Machine Learning with TinyML
• RoboRun: A Robot Runtime to Exploit Spatial Heterogeneity
• The Role of Compute in Autonomous Aerial Vehicles
• Robomorphic Computing: A Design Methodology for Domain-Specific Accelerators Parameterized by Robot Morphology
• Accelerating Robot Dynamics Gradients on a CPU, GPU, and FPGA
• Application of Approximate Matrix Multiplication to Neural Networks and Distributed SLAM
• Realtime Model Predictive Control using Parallel DDP on a GPU
• A Performance Analysis of Parallel Differential Dynamic Programming on a GPU
• Parallel and Constrained Differential Dynamic Programming for Model Predictive Control
• Constrained Unscented Dynamic Programming
• Project-based, collaborative, algorithmic robotics for high school students: Programming self-driving race cars at MIT
• Hacking the White House: Election Fraud in the Digital Age