Автономные роботы: принципы работы и перспективы развития.

Robot that performs behaviors or tasks with a high degree of autonomy
An autonomous robot is a robot that acts without recourse to human control. Historic examples include space probes. Modern examples include self driving vacuums and cars. Industrial robot arms that work on assembly lines inside factories may also be considered autonomous robots, though their autonomy is restricted due to a highly structured environment and their inability to locomote.

The first requirement for complete physical autonomy is the ability for a robot to take care of itself. Many of the battery powered robots on the market today can find and connect to a charging station, and some toys like Sony's Aibo are capable of self docking to charge their batteries. Self maintenance is based on "proprioception", or sensing one's own internal status. In the battery charging example, the robot can tell proprioceptively that its batteries are low and it then seeks the charger. Another common proprioceptive sensor is for heat monitoring. Increased proprioception will be required for robots to work autonomously near people and in harsh environments. Common proprioceptive sensors include thermal, optical, and haptic sensing, as well as the Hall effect (electric).

Exteroception is sensing things about the environment. Autonomous robots must have a range of environmental sensors to perform their task and stay out of trouble. The autonomous robot can recognize sensor failures and minimize the impact on the performance caused by failures. Common exteroceptive sensors include the electromagnetic spectrum, sound, touch, chemical (smell, odor), temperature, range to various objects, and altitude. Some robotic lawn mowers will adapt their programming by detecting the speed in which grass grows as needed to maintain a perfectly cut lawn, and some vacuum cleaning robots have dirt detectors that sense how much dirt is being picked up and use this information to tell them to stay in one area longer.

The next step in autonomous behavior is to actually perform a physical task. A new area showing commercial promise is domestic robots, with a flood of small vacuuming robots beginning with iRobot and Electrolux in 2002. While the level of intelligence is not high in these systems, they navigate over wide areas and pilot in tight situations around homes using contact and non contact sensors. Both of these robots use proprietary algorithms to increase coverage over simple random bounce. The next level of autonomous task performance requires a robot to perform conditional tasks. For instance, security robots can be programmed to detect intruders and respond in a particular way depending upon where the intruder is. For example, Amazon (company) launched its Astro for home monitoring, security and eldercare in September 2021.

For a robot to associate behaviors with a place (localization) requires it to know where it is and to be able to navigate point to point. Such navigation began with wire guidance in the 1970s and progressed in the early 2000s to beacon based triangulation. Current commercial robots autonomously navigate based on sensing natural features. The first commercial robots to achieve this were Pyxus' HelpMate hospital robot and the CyberMotion guard robot, both designed by robotics pioneers in the 1980s. These robots originally used manually created CAD floor plans, sonar sensing and wall following variations to navigate buildings. The next generation, such as MobileRobots' PatrolBot and autonomous wheelchair, both introduced in 2004, have the ability to create their own laser based maps of a building and to navigate open areas as well as corridors. Their control system changes its path on the fly if something blocks the way. At first, autonomous navigation was based on planar sensors, such as laser range finders, that can only sense at one level. The most advanced systems now fuse information from various sensors for both localization (position) and navigation. Systems such as Motivity can rely on different sensors in different areas, depending upon which provides the most reliable data at the time, and can re map a building autonomously. Rather than climb stairs, which requires highly specialized hardware, most indoor robots navigate handicapped accessible areas, controlling elevators, and electronic doors. With such electronic access control interfaces, robots can now freely navigate indoors. Autonomously climbing stairs and opening doors manually are topics of research at the current time. As these indoor techniques continue to develop, vacuuming robots will gain the ability to clean a specific user specified room or a whole floor. Security robots will be able to cooperatively surround intruders and cut off exits. These advances also bring concomitant protections: robots' internal maps typically permit "forbidden areas" to be defined to prevent robots from autonomously entering certain regions.

As autonomous robots have grown in ability and technical levels, there has been increasing societal awareness and news coverage of the latest advances, and also some of the philosophical issues, economic effects, and societal impacts that arise from the roles and activities of autonomous robots. Elon Musk, a prominent business executive and billionaire has warned for years of the possible hazards and pitfalls of autonomous robots; however his own company is one of the most prominent companies that is trying to devise new advanced technologies in this area. In 2021, a United Nations group of government experts, known as the Convention on Certain Conventional Weapons – Group of Governmental Experts on Lethal Autonomous Weapons Systems, held a conference to highlight the ethical concerns which arise from the increasingly advanced technology for autonomous robots to wield weapons and to play a military role.

The first autonomous robots were known as Elmer and Elsie, constructed in the late 1940s by W. Grey Walter. They were the first robots programmed to "think" the way biological brains do and were meant to have free will. Elmer and Elsie were often labeled as tortoises because of how they were shaped and the manner in which they moved. They were capable of phototaxis, the movement that occurs in response to light stimulus.

Lethal autonomous weapons (LAWs) are a type of autonomous robot military system that can independently search for and engage targets based on programmed constraints and descriptions. LAWs are also known as lethal autonomous weapon systems (LAWS), autonomous weapon systems (AWS), robotic weapons, killer robots or slaughterbots. LAWs may operate in the air, on land, on water, under water, or in space. The autonomy of current systems as of 2018 was restricted in the sense that a human gives the final command to attack though there are exceptions with certain "defensive" systems. UGV Interoperability Profile (UGV IOP), Robotics and Autonomous Systems – Ground IOP (RAS G IOP), was originally a research program started by the United States Department of Defense (DoD) to organize and maintain open architecture interoperability standards for Unmanned Ground Vehicles (UGV). The IOP was initially created by U. S. Army Robotic Systems Joint Project Office (RS JPO):
In October 2019, Textron and Howe & Howe unveiled their Ripsaw M5 vehicle, and on 9 January 2020, the U. S. Army awarded them a contract for the Robotic Combat Vehicle Medium (RCV M) program. Four Ripsaw M5 prototypes are to be delivered and used in a company level to determine the feasibility of integrating unmanned vehicles into ground combat operations in late 2021. It can reach speeds of more than , has a combat weight of 10.5 tons and a payload capacity of The RCV M is armed with a 30 mm autocannon and a pair of anti tank missiles. The standard armor package can withstand 12.7×108mm rounds, with optional add on armor increasing weight to up to 20 tons. If disabled, it will retain the ability to shoot, with its sensors and radio uplink prioritized to continue transmitting as its primary function. Crusher is a autonomous off road Unmanned Ground Combat Vehicle developed by researchers at the Carnegie Mellon University's National Robotics Engineering Center for DARPA. It is a follow up on the previous Spinner vehicle. DARPA's technical name for the Crusher is Unmanned Ground Combat Vehicle and Perceptor Integration System, and the whole project is known by the acronym UPI, which stands for Unmanned Ground Combat Vehicle PerceptOR Integration. The Warrior is primarily envisioned for the Indian Air Force use and a similar, smaller version will be designed for the Indian Navy. It would be controlled by the mothership and accomplish tasks such as scouting, absorbing enemy fire, attacking the targets if necessary with its internal & external pylons weapons or sacrifice itself by crashing into the target. The SGR A1 is a type of autonomous sentry gun that was jointly developed by Samsung Techwin (now Hanwha Aerospace) and Korea University to assist South Korean troops in the Korean Demilitarized Zone. It is widely considered as the first unit of its kind to have an integrated system that includes surveillance, tracking, firing, and voice recognition. While units of the SGR A1 have been reportedly deployed, their number is unknown due to the project being "highly classified".

Tesla Robot and NVIDIA GR00T are humanoid robots.

A delivery robot is an autonomous robot used for delivering goods.

An Automatic Charging Robot, unveiled on July 27, 2022, is an arm shaped automatic charging robot, charging an electric vehicle. It has been running a pilot operation at Hyundai Motor Group's headquarters since 2021. VISION AI System based on deep learning technology has been applied. When an electric vehicle is parked in front of the charger, the robot arm recognizes the charger of the electric vehicle and derives coordinates. And automatically insert a connector into the electric car and operate fast charging. The robot arm is configured in a vertical multi joint structure so that it can be applied to chargers at different locations for each vehicle. In addition, waterproof and dustproof functions are applied.

Construction robots are used directly on job sites and perform work such as building, material handling, earthmoving, and surveillance.

Research and education mobile robots are mainly used during a prototyping phase in the process of building full scale robots. They are a scaled down versions of bigger robots with the same types of sensors, kinematics and software stack (e. g. ROS). They are often extendable and provide comfortable programming interface and development tools. Next to full scale robot prototyping they are also used for education, especially at university level, where more and more labs about programming autonomous vehicles are being introduced.

In March 2016, a bill was introduced in Washington, D. C., allowing pilot ground robotic deliveries. The program was to take place from September 15 through the end of December 2017. The robots were limited to a weight of 50 pounds unloaded and a maximum speed of 10 miles per hour. In case the robot stopped moving because of malfunction the company was required to remove it from the streets within 24 hours. There were allowed only 5 robots to be tested per company at a time. A 2017 version of the Personal Delivery Device Act bill was under review as of March 2017. In February 2017, a bill was passed in the US state of Virginia via the House bill, HB2016, and the Senate bill, SB1207, that will allow autonomous delivery robots to travel on sidewalks and use crosswalks statewide beginning on July 1, 2017. The robots will be limited to a maximum speed of 10 mph and a maximum weight of 50 pounds. In the states of Idaho and Florida there are also talks about passing the similar legislature. It has been discussed that robots with similar characteristics to invalid carriages (e. g. 10 mph maximum, limited battery life) might be a workaround for certain classes of applications. If the robot was sufficiently intelligent and able to recharge itself using the existing electric vehicle (EV) charging infrastructure it would only need minimal supervision and a single arm with low dexterity might be enough to enable this function if its visual systems had enough resolution. In November 2017, the San Francisco Board of Supervisors announced that companies would need to get a city permit in order to test these robots. In addition, the Board banned sidewalk delivery robots from making non research deliveries.