Oren Gal

Efficient and safe on-line motion planning in dynamic environments

This paper presents a new on-line planner for dynamic environments that is based on the concept of Velocity Obstacles (VO). It addresses the issue of motion safety, i.e. avoiding states of inevitable collision, by selecting a proper time horizon for the velocity obstacle. The proper choice of the time horizon ensures that the boundary of the velocity obstacle coincides with the boundary of the set of inevitable collision states. This time horizon is determined by the minimum time it would take the robot to avoid collision, either by stopping or by passing the respective obstacle. The planner generates a near-time optimal trajectory to the goal by selecting at each time step the velocity that minimizes the time-to-go and is out of the velocity obstacle. The planner takes into account the shape, velocity, and path curvature of the obstacles trajectory. It is demonstrated for on-line motion planning in very crowded static and dynamic environments.

Adaptive time horizon for on-line avoidance in dynamic environments

This paper addresses the issue of motion planning in dynamic environments using Velocity Obstacles. Specifically, we propose an adaptive time horizon to truncate the velocity obstacle so that its boundary closely, yet conservatively, approximates the boundary of the set of states from which collision is unavoidable. We wish to develop a representation such that any velocity vector that does not penetrate the velocity obstacle is safe, i.e. an avoidance maneuver exists, and any that does is not. Such clear partitioning between safe and unsafe velocities would allow safe planning with only one step look ahead, and can produce faster trajectories than the conservative trajectories produced when using an infinite time horizon. The computation of the adaptive time horizon is formulated as a minimum time problem, which is solved numerically for each static or moving obstacle. It is used in an on-line planner that generates locally time optimal trajectories to the goal. The planner is demonstrated for static and moving obstacles, and for on-line motion planning in a crowded dynamic environment.

Automatic Obstacle Detection for USV’s Navigation Using Vision Sensors

This paper presents an automatic method to acquire, identify, and track obstacles from an Unmanned Surface Vehicle (USV) location in marine environments using 2D Commercial Of The Shelf (COTS) video sensors, and analyzing video streams as input. The guiding line of this research is to develop real-time automatic identification and tracking abilities in marine environment with COTS sensors. The output of this algorithm provides obstacle’s location in x-y coordinates. The ability to recognize and identify obstacles becomes more essential for USV’s autonomous capabilities, such as obstacle avoidance, decision modules, and other Artificial Intelligence (AI) abilities using low cost sensors. Our algorithm is not based on obstacles characterization. Algorithm performances were tested in various scenarios with real-time USV’s video streams, indicating that the algorithm can be used for real-time applications with high success rate and fast time computation.

Tracking Objects Using PHD Filter for USV Autonomous Capabilities

Most of the work on automatic detection tracking and classification of unmanned applications over the past twenty years has been focused on ground and aerial vehicles. Recently, the research has also focused on unmanned surface and underwater vehicles for autonomous capabilities.The ability to recognize and identify obstacles becomes more essential with USVs autonomous capabilities, such as obstacle avoidance, decision modules, and other Artificial Intelligence (AI) abilities using low cost sensors. This paper presents multi-target automatic algorithm stages to acquire, identify, and track targets from an Unmanned Surface Vehicle (USV) located in marine environments with LIDAR sensor challenging clutter. We present several clutter models and formulations to handle clutter phenomena. We propose the Probability Hypothesis Density (PHD) Bayes filter, challenging clutter for multi-target tracking.

Safe Navigation in Dynamic Environments

This paper addresses the issue of motion safety for on-line navigation in dynamic environments. Using velocity obstacles to represent the dynamic environment, we propose to truncate the velocity obstacle by the minimum time horizon, computed to ensure that the velocity obstacle is truncated close to the boundary of the set of inevitable collision states. Thus, using the velocity obstacle to select potential avoidance maneuvers would ensure that only safe maneuvers are being selected. The concept of velocity obstacles was known for some time, but the issue of how to truncate it without compromising safety was not addressed until recently. The computation of the minimum time horizon is formulated as a minimum time problem, which is solved numerically for each static or moving obstacle. The “safe” velocity obstacles are used in an on-line planner that generates near-time optimal trajectories to the goal. The planner is demonstrated for on-line motion planning in very crowded static and dynamic environments.

Multi-agents Decision Making Concept for Multi-missions Applications in Marine Environments

This paper presents unique multi-agents decision making and control concept in marine environments, formulating distributed and centralized approach. We map several major missions and introduce the conceptual implementations using multi-agents: patrolling in predefined area, reaching specific destination, following or monitoring specific object and getting back to home harbor. We present our algorithm scheme with logical concept of each module and simulate agent’s sensing capability. We demonstrate our concept in several scenarios simulations with advanced test-bed environment. Algorithm performances are also analyzed showing real-time running time.

Patrolling Strategy Using Heterogeneous Multi Agents in Urban Environments Using Visibility Clustering

In this paper, we study the Visible Trajectories Planning for Patrolling application using heterogeneous multi agents in 3D urban environments. Our concept is based on a spatial clustering method using visibility analysis of the 3D visibility problem from viewpoints in 3D urban environments, defined as locations. We consider two kinds of agents, with different kinematic and perception capabilities. Using a simplified version of Traveling Salesman Problem (TSP), we formulate the problem as one of patrolling strategy, with upper boundary optimal performances. We present a combination of relative deadline UniPartition approaches based on visibility clusters. These key features allow new planning for an optimal patrolling strategy for heterogeneous agents in urban environments. We demonstrate our patrolling strategy method in simulations using Autonomous Navigation and Virtual Environment Laboratory (ANVEL) test bed environment.

Unified Trajectory Planning Algorithms for Autonomous Underwater Vehicle Navigation

This paper presents two efficient methods for obstacle avoidance and path planning for Autonomous Underwater Vehicle (AUV). These methods take into account the dynamic constraints of the vehicle using advanced simulator of AUV considering low level control and stability effects. We present modified visibility graph local avoidance method and a spiral algorithm for obstacle avoidance. The algorithms were tested in challenged scenarios demonstrating safe trajectory planning.