A framework for planning motion in environments with moving obstacles

In this paper we present a heuristic approach to planning in an environment with moving obstacles. Our approach assumes that the robot has no knowledge of the future trajectory of the moving objects. Our framework also distinguishes between two types of moving objects in the environment: hard and soft objects. We distinguish between the two types of objects in the environment as varying application domains could allow for some collision between some types of moving objects. For example, a robot planning a path in an environment with people could have the people modeled as circular disks with a safe zone surrounding each person. Although the robot may try to stay out of each safe zone, violating that criteria would not necessarily result in planning failure. We will show the effectiveness of our planner in general dynamic environments with the soft objects having varying behaviors.

Authors

• Samuel Rodríguez
• Jyh-Ming Lien
• Nancy M. Amato

Keywords

• Path planning
• Robotics and automation
• Motion planning
• Virtual reality
• Intelligent robots
• USA Councils
• Graphics
• Application software
• Computer science
• Dynamic Environment
• Hard Objects
• Soft Objects
• Urban Planning
• Planning Process
• Number Of Objects
• Translational Motion
• Rotational Motion
• Planning Stage
• Space Environment
• Environmental Agents
• Planning Time
• Static Environment
• Goal Position
• Local Path
• Global Path
• Planning Steps
• Robot Path
• Attack Behavior
• Safe Path
• Rapidly-exploring Random Tree
• Valid Path
• Neighboring Agents
• Static Objects
• Basis Of Behavior
• Two-stage Approach
• Planning Phase