Our research investigates the complex task of multiple autonomous agents learning to coordinate and deliver packages in warehouse environments--a problem requiring implicit communication, collision avoidance, and efficient task allocation without centralized control. Traditional warehouse automation relies on centralized planning systems that face scalability limitations; multi-agent reinforcement learning (MARL) offers an alternative through decentralized learned policies, but requires solving the credit assignment problem. We compare MARL algorithms on warehouse coordination: QMIX [Rashid et al., 2018] (value decomposition), IPPO (independent learning), and MASAC (centralized critic). Our study progresses from MPE for validation to RWARE for warehouse evaluation, culminating in Unity 3D deployment where agents demonstrate learned package delivery behavior. QMIX emerged as the best performer after systematic comparison. Our contributions: (1) hyperparameter analysis showing default configurations fail on sparse-reward warehouse tasks, (2) comparative evaluation across algorithms and scales, (3) Unity ML-Agents integration demonstrating sim-to-sim transfer with successful package delivery, and (4) identification of scaling challenges. Full experimental details and results are documented in our Quarto documentation book. 1

The project we embarked on is making an electronic robot that can deliver a package along a set route through infrared sensors. It uses the infrared sensors to determine if the path it is following is correct or if it is off course. This is determined by sending off a photon to reflect off the path and determines if it is on a light surface by the amount of light emitted back or if it is a dark surface by the amount of light that is not present. In addition to following a line, the user can stop and start the robot at any interval through the infrared remote control. The project is a combination of the practical parts of machinery with the software part of coding in Arduino which is a coding subsect of C++. This can lead to endless possibilities that could help a wide variety of people from all ranges of life, especially with those that live with disabilities

Amazon has unveiled its newest delivery drone that will soon be dropping packages from 12 feet in the air in two U.S. cities. The retail giant has long wanted to solve the last leg of package delivery, especially since it launched Amazon Prime's Two-Day delivery offering in 2005. Jeff Bezos first announced drone delivery in 2013, but the service only made a single delivery three years after that. The drone, dubbed MK27-2, will start making deliveries in Lockeford, California, and College Station, Texas, by the end of 2022. The autonomous craft is about five-and-a-half feet in diameter, weighs 80 pounds and can only carry packages that weight less than five pounds.

Unmanned Aerial Vehicles grow more popular by the day and applications for them are crossing boundaries of science and industry, with everything from aerial photography to package delivery to disaster management benefiting from the technology. But before they become commonplace, there are challenges to be solved to make them reliable and safe. The following paper discusses the challenges associated with the precision landing of an Unmanned Aerial Vehicle, including methods for sensing and control and their merits and shortcomings for various applications.

As UAV technology improves, more uses have been found for these versatile autonomous vehicles, from surveillance to aerial photography, to package delivery, and each of these applications poses unique challenges. This paper implements a solution for one such challenge: To land on a moving target. This problem has been addressed before with varying degrees of success, however, most implementations focus on indoor applications. Outdoor poses greater challenges in the form of variables such as wind and lighting, and outdoor drones are heavier and more susceptible to inertial effects. Our approach is purely vision based, using a monocular camera and fiducial markers to localize the drone and a PID control to follow and land on the platform.

Pizza-making robots are already here, and taking a pizza order is trivial for any half-decent chatbot. But if you're waiting for a robot to deliver your'za, you may be waiting for a while. It's not because autonomous navigation technology doesn't exist -- it's that the data set required to run it is too specific. Digital maps can lead a robot to your driveway, but there are no detailed directions from the curb to your door. Currently, robots rely on humans to manually map the environments in which they work.

Members of the public are getting the chance to take a free ride in a self-driving car in Detroit as part of a nonprofit coalition's effort to clear up misunderstanding and confusion about the technology (April 5) AP, AP Fully autonomous vehicles that can drive themselves in nearly any situation aren't roaming the streets just yet, but almost every major technology company and automaker is working on getting to that point as quickly as possible. These companies are making huge strides in creating a world where we can hop into a car, tell it where to take us, and safely arrive – with no human input needed. If you need some convincing about how these vehicles will transform our world, consider these four hard-to-believe facts. Research from IHS Markit shows that in nearly two decades, more than 30 million self-driving vehicles will be sold each year. That means that 26% of new cars will have autonomous mobility by that year.

The first time you see a strange robot walking down your street, it might be delivering a parcel. That's the future envisioned by Ford in a new research project that explores how robots and self-driving cars could work together to deliver groceries, fast food, and more. The robot in question is called Digit, and it stands just over five feet tall. It has a pair of skeletal legs, two arms ending in shapeless nubs, and a sensor array where its head should be. It's the creation of startup Agility Robotics, which has been developing bipedal robots since 2015 when the company was spun out of research from Oregon State University.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Using machine-learning and sensory hardware, Alberto Rodriguez, assistant professor of mechanical engineering, and members of MIT's MCube lab have developed a robot that is learning how to play the game Jenga. The technology could be used in robots for manufacturing assembly lines.

Germany automotive firm Continental is best know for its tires, but at CES 2019 the company is demonstrating something a little different: package delivery by robot dog. As part of its research into the future of mobility, Continental has partnered with robotics company ANYbotics (a spin off from ETH Zurich) to imagine the future of package delivery. In a staged demonstration on the CES show floor, the firm showed how one of ANYbotics' four-legged robots could jump out the back of a self-driving delivery truck and carry a package right up to someone's front door. In the demo, the ANYMal robot could be seen slowly picking its way over debris in the garden before ringing the fake doorbell with one if its limbs. It then tips the package off its back onto the porch and performs a little victory dance as a bonus.