Related Experiment Video
Updated: Jan 18, 2026
11:53
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
12.2K
Risk-Aware Reinforcement Learning with Dynamic Safety Filter for Collision Risk Mitigation in Mobile Robot Navigation
Bingbing Guo1, Guina Wang1, Yiyang Chen1
1School of Mechanical and Electrical Engineering, Soochow University, Suzhou 215137, China.
Sensors (Basel, Switzerland)
|September 13, 2025
Summary
Mobile robots can now navigate dynamic environments safely using a new risk-aware method. This approach combines policy optimization with barrier functions for effective obstacle avoidance and improved mission success.
Area of Science:
- Robotics
- Artificial Intelligence
- Control Systems
Background:
- Traditional mobile robot navigation methods struggle with safety and adaptability in dynamic environments.
- Predefined rules in navigation limit real-time, flexible obstacle avoidance in complex scenarios.
Purpose of the Study:
- To develop a novel method for safe and adaptive obstacle avoidance in mobile robots operating in dynamic environments.
- To enhance the safety and efficiency of mobile robot navigation through advanced policy optimization and control barrier functions.
Main Methods:
- Proposed a risk-aware, dynamic, adaptive regulation barrier policy optimization (RADAR-BPO) method.
- Integrated proximal policy optimization (PPO) for exploratory actions with control barrier function (CBF) for real-time safety filtering.
- Utilized quadratic programming to minimize risky actions and ensure navigation efficiency.
Main Results:
- Achieved a nearly 90% obstacle avoidance success rate in complex, dynamic, multi-obstacle environments.
- Demonstrated improved overall mission success rates in ROS Gazebo simulations.
- Validated the robustness and effectiveness of RADAR-BPO in challenging dynamic scenarios.
Conclusions:
- The RADAR-BPO method effectively addresses safety and adaptability limitations in mobile robot navigation.
- The integration of PPO and CBF provides a robust solution for real-time, safe obstacle avoidance.
- The proposed method significantly enhances mobile robot performance in complex dynamic environments.
Related Concept Videos
01:17Rolling Resistance: Problem Solving
785
Rolling resistance, also known as rolling friction, is the force that resists the motion of a rolling object, such as a wheel, tire, or ball, when it moves over a surface. It is caused by the deformation of the object and the surface in contact with each other, as well as other factors like internal friction, hysteresis, and energy losses within the materials. Rolling resistance opposes the object's motion, requiring additional energy to overcome it and maintain movement. In practical...
785
01:14Avoidance Learning and Learned Helplessness
2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K