Safety assessment of robot trajectories for navigation in uncertain and dynamic environments

Abstract

This paper presents a probabilistic framework for reasoning about the safety of robot trajectories in dynamic and uncertain environments with imperfect information about the future motion of surrounding objects. For safety assessment, the overall collision probability is used to rank candidate trajectories by considering the probability of colliding with known objects as well as the estimated collision probability beyond the planning horizon. In addition, we introduce a safety assessment cost metric, the probabilistic collision cost, which considers the relative speeds and masses of multiple moving objects in which the robot may possibly collide with. The collision probabilities with other objects are estimated by probabilistic reasoning about their future motion trajectories as well as the ability of the robot to avoid them. The results are integrated into a navigation framework that generates and selects trajectories that strive to maximize safety while minimizing the time to reach a goal location. An example implementation of the proposed framework is applied to simulation scenarios, that explores some of the inherent computational tradeoffs.

On Provably Safe Obstacle Avoidance for Autonomous Robotic Ground Vehicles

“…With the increased introduction of autonomous robotic ground vehicles as consumer products-such as autonomous household appliances [7] or driverless cars on regular Californian roads 1 -we face an increased need for ensuring safety not only for the sake of the consumer, but also the manufacturer. Since those robots are designed for environments that occupy stationary as well as moving obstacles, motion safety and obstacle avoidance are vital safety features for such robots [3,22,25,27].…”

“…Unlike existing work on obstacle avoidance (e. g., [1,17,[24][25][26]), we use hybrid models and verification techniques that describe and verify the robot's discrete control choices along with its continuous, physical motion. In summary, our contributions are (i) hybrid models of navigation and obstacle avoidance control algorithms of robots, and (ii) proofs that they guarantee passive and passive friendly safety in the presence of stationary and moving obstacles despite sensor and actuator uncertainty.…”

A Cross-Domain Survey of Metrics for Modelling and Evaluating Collisions

“…Though comparative metrics exist for assessing the safety of specific systems, most are neither generalizable nor fully applicable across domains. Such metrics focus on equating safety with single-focus factors such as separation distance [110,111], impact force [112][113][114][115], system configuration and velocity [116], inertia [117], and cost [118]. As a result, these metrics risk falling short of their full potential by not taking into account the lessons learned by other fields of study.…”

A risk assessment infrastructure for powered wheelchair motion commands without full sensor coverage

“…Domain-specific risk evaluation measures have also been applied to ensure task safety in human-robot dialog [20]. Another probabilistic model for safety assessment in dynamic environments under an imperfect sensing model was proposed in [21].…”