28 Jan

Mean-field Improvement1: add the observation range

Zida Wu

This improvement is based on the previous posts, corresponding to the first step: Step 1: Deal with information problem: using only closest neighborhood information. Code is here The main improvent is to set the observation field. Current mean-field assumes all agents' information are av...

28 Jan

Board Design Tools for the 21st Century and Introductions

Richard Lin (Ducky)

Hi everyone! I'm a new postdoc with LEMUR, and I'll be working on modern tools for circuit board level electronics design. So that's a lot of words, let's unpack that. Modern board design tools (like KiCad) consist of schematic capture (drawing the schematic) followed by layout (placing components...

24 Jan

FORAY - Setup the prototype

Zhaoliang Zheng

This week, we started to get all the new members know how to build a blimp from sketch. Next week, we will be working on the altitude control using ultrasonic sensor. Meanwhile, some ideas that we are thinking about: (1) Modify the propulsion system, use only 1 motors at the side of blimp...

20 Jan

Test result: Mean-field Multi-agent Reinforcement Learning Platform

Zida Wu

Paper Target: IROS 2022 Current open source mean-field reinforcement learning code, which is based on MAgent Blue: Group 1 (Proposed Algorithm)Red: Group 2 (Opponent) Algorihtm Information Collision Task Current using all agents as neighborhood One state (position) only...

11 Jan

How to use git for collaborative code development

Zhaoliang Zheng

Problems that I've been thinking about: How can collaborative code development be more efficient? How do avoid conflict when multiple people are developing? How make the code more readable, easy to maintain and debug? A successful Git branching model: (Simplified version) A example...

07 Jan

What is a Quantum Kalman Filter?

Cody Fan

A quantum Kalman filter is a recursive Bayesian filter used to predict and estimate the state of a quantum system, and was first introduced by Viacheslav Belavkin. It is described in his work (Belavkin, 1999). Another interesting work is the quantum extended Kalman filter. However, much of the r...

07 Dec

Make RoCo WMR work with .wbo outputs and outline for new modules

Anwesha Chattoraj

Tasks to finish before 16/12/2021 These tasks mostly to get to speed on the roco pipeline and begin work on adding new modules Build and fix existing cars to produce .wbo output in the Device branch. Making the API compatible to work with it. Build some new WMR models Figure out why one pytest...

30 Nov

Multi-agent Reinforcement Learning Environments

Zida Wu

30 Nov

Distributed optimization

Tsang-Kai Chang

Last week, I explained why typical distributed gradient descent leads to inexact solution, even though the convergence rate is linear (in log scale). There is a very important paper that shows that we can in fact have exact solution by incorporating the previous gradient. This algorithm is called...

09 Nov

Review: automated controller generation

Anwesha Chattoraj

proposal writing Focus Implementing a generalized control and planning output for arbitrary folded robots designs generated by a computational design framework Approach I am looking at papers that are focusing on generating the kinematic and dynamic model of robots with modular components (...

Search

Popular Tags

foray origami robots blimp vr ducky SLAM computer vision edg computational design roco Origami rocolib slam design Motion Planning simulation RoCo arduino Robot Compiler edg-model autonomy reinforcement learning; multi-agent; mean-field; create; kalman filter; mesh logics friction tank contacts esp32 mesh network motors networking imu communication pushing dynamics esp now multi-agent wireless control visual processing machine learning auxetic structure path planning Robotica ROCO computer skill reinforcement learning openmv cars webapp i2c surface structure DARPA pcbs power consumption origami motor modeling Battery dataset test dash visual odometry port-arrays frequency diversity bistable auxetic auxetics gestural interface feedback controller unit cell gondola crawler semantic infrastructure robot mixed reality gestural intuition paper Consensus machine vision control sensors 433mhz apriltags perception FORAY DER icra2021 darpa; create; Quantum Information create; kalman filter; EM; radio 4-wheeled open house Foray network structures refactoring propeller crazyflie lidar Kullback-Leibler Divergence environmental design logic optimization altimeter matlab lasercutter nodemcu integration test joystick pushing problem motor configuration offline reinforcement learning modeling contacts tutorial exam legs or gate PCB webots object detection localization simulink von Mises Fisher Distribution conference UAV IR project management Auxetics thrust painlessmesh ros2 research proposal RL multi-agent path planning mesh networking balloon test arduino nano experiment results blynk distributed optimization rviz2 decentralized arnhold gazebo vision processing fusionbot swarm 3D-CHESS; PVDF conferences edg-refactoring misc ceres chiral debug release coriolis force wtf nylon proposal deep learning interpolation wireless signal strength reinforcement learning; multi-agent; decentralized demo video pvdf dynamic model creative internal newton's method pdms quasi-static pushing sma-based actuator nonholonomic systems Euler-Bernoulli beam system ID grant feedback-controlled controls trajectory optimization vision ML Computer skill spring-mass der PDMS kalman filter; multi-agent path finding Learning kinematic_model mean field; reinforcement learning 2.4 GHz 433 MHz liquid crystal elastomer flytrap pivoting papers Machine Learning elastic polymers paper cutter plastic Zeem reinforcement learning; ide material inkscape rhino surfaces Q-Learning Nylon 6 Model-Free reinforcement learning; multi-agent; mean-field; stationary concept solar cars deployment cell grid fabrication boat square unit cell optitrack adaptive control steering Characterization tool structured field hot plates differential power detectionrate distance shape color edg-ide pain surface contact reservoir computing peripheral device keyboard swarm control car von Mises-Fisher von Mises Fisher port-array quasi-static modeling Kalman Filter Consensus Algorithms edg-compiler silicone reinforcement learning; multi-agent; python lab_data #activecapturingmechanism #claw buoyancy equations in-situ design boxboat tracking code slam; flowchart; writing balloon actuation integration flapping color_segmentation result firmware segmentation on multiple object and centers finding competition prelab multirobot system multiple blimps pid defender integrated system 3d printing catching mechanism kalman filter barometer detection protobuf thrust configuration depth estimation von Mises Distribution sensor fusion HDL board design von Mises-Fisher Distributions Bessel functions battery current sensor ZMP center of friction game theory cameras Multi-Agent Systems Barycenter buoyancy model prediction model-based RL bootstrapping Bayesian networks ensemble methods offline Rl hardware manipulation COVID 19 ESP32 multi-robot state space marginal cost pricing delta tolling pressure distribution lift force cad serial monitor dynamic modeling preliminary exam multiple devices multi-object tracking semantic segmentation instance segmentation reinforcement learning; multi-agent; mean-field; game theory; current Xbee Zigbee robot compiler origami robot spi neural network literature review presentations multipack 433 contact surp paper review Writing motorized boats throughput range IROS Integrated Demo slam; paper review Short Post edg-examples machine training codesign solidworks ICML design tool pixracer pixhawk ardupilot flight controller regression fly test motor distribution signal strength Python DNN ICLR ICRA guassian processes scenic probabilistic neural networks graph generators MBRL Synthesizable Radio batch learning ros multirobot motor driver MIMO communications rssi submission point cloud 2.4ghz latency Silicon