Artificial Intelligence based human following mobile robot
Person following scenarios arise when a human and an autonomous robot collaborate on a common task that requires the robot to follow the human. Knowledge about presence, position, and motion state of people will enable the robot to better understand and anticipate intentions and actions. G
2025-06-28 16:30:18 - Adil Khan
Artificial Intelligence based human following mobile robot
Project Area of Specialization RoboticsProject SummaryPerson following scenarios arise when a human and an autonomous robot collaborate on a common task that requires the robot to follow the human. Knowledge about presence, position, and motion state of people will enable the robot to better understand and anticipate intentions and actions. Ground service robots following a human while performing a cooperative task is the canonical example of person following robots. Such assistant robots are being used in many domestic and industrial applications, the entertainment industry, defense and social interactions, and in health care.
Therefore, basic theme of our project is to design an autonomous mobile robot that is able to detect and follow a person using 2D LIDAR as main sensor and Raspberry PI as its brain. To perform this task accurately, robot needs a mechanism that enables it to visualize the person and act/move accordingly. The robot must be intelligent enough to follow a person in indoor environment in presence of static as well as dynamic obstacle.
Project Objectives- Detection of target (human).
- Following the target.
- Dynamic and static obstacle avoidance.
With a growing number of robots deployed in populated environments, the ability to detect and track humans and recognize their activities are key components for future service robots. There are many solutions in the literature that try to solve this problem using a multi-modal approach, typically with vision and range sensors, but these kinds of approaches are very expensive both from the point of view of the cost of the sensor and the computing capabilities needed for processing and integrating, and are more likely to generate contradictory information. Moreover, laser range finders provide a large field of view and, opposed to vision, are mainly independent from ambient conditions. For this reason, systems based only on range sensors are more desirable. Therefore, we are proposing the idea of a person following robot using 2D LIDAR. An intelligent decision is being made by the robot control unit based on the information obtained from LIDAR data, hence detecting and following the target.
Benefits of the ProjectThe most appealing beneficiary of human following robot are us, HUMANS!
Human life safety and human ease holds its preference in comparison to any other objective in the world. Nowadays with increase in danger to their life, in the form of natural disaster and fluctuation in weather cycle, leaves their life at high risk. Our motivation is the belief that human safety and their rescue as well as their ease holds first preference if any of these mishaps happen in any part of the world, but with lagging useful techniques to get the first information which plays a critical role in rescuing, it is essential to get these information as early as possible without any loss to human life. A human-following function can allow a robot to be ahuman assistant under various situations, such as accompanyingrunners or actingas a travel guide. Robots willno longer play the role of workers, but will be the friendsof humankind. That is, the human-following capability is a significantpart of the interactionbetween robots and people. Therefore, as mentioned earlier, such assistant robots can be being used in any domestic and industrial application, the entertainment industry, defense and social interaction, and in health care.
Technical Details of Final DeliverableFinal deliverable of the project is a prototype hardware system/robot which will perform following tasks:
- It will detect and follow the targeted person.
- If a passerby crosses the path with the targeted person, robot will continue to follow its target.
- It will be able avoid (if any) static as well as dynamic obstacles in its way.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 40000 | |||
| RP LIDAR A1 | Equipment | 1 | 19000 | 19000 |
| Raspberry pi 3B | Equipment | 1 | 6200 | 6200 |
| Motors | Equipment | 2 | 2500 | 5000 |
| Robot chasis | Equipment | 1 | 2000 | 2000 |
| Motor drivers | Equipment | 1 | 600 | 600 |
| DC battery | Equipment | 1 | 3500 | 3500 |
| Arduino UNO | Equipment | 1 | 700 | 700 |
| Miscellaneous | Miscellaneous | 1 | 3000 | 3000 |