Safe Stochastic Planning: Planning to Avoid Fatal States

نویسندگان

Hao Ren

Ali Akhavan Bitaghsir

Mike Barley

چکیده

Markov decision processes (MDPs) are applied as a standard model in Artificial Intelligence planning. MDPs are used to construct optimal or near optimal policies or plans. One area that is often missing from discussions of planning under stochastic environment is how MDPs handle safety constraints expressed as probability of reaching threat states. We introduce a method for finding a value optimal policy satisfying the safety constraint, and report on the validity and effectiveness of our method through a set of experiments.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Predictive Planning for a Mobile Robot in Human Environments

Generating short and safe paths for mobile robots operating in crowded spaces is a hard task due to the high uncertainty of each person’s future behaviour. Classical path planning approaches often result in an over-constrained or overly cautious robot that fails to produce a feasible, safe path in the crowd, or plans a large, sub-optimal detour to avoid people in the scene. This work addresses ...

متن کامل

Mapping Obstacles to Collision States for On-line Motion Planning in Dynamic Environments

This paper presents a representation of static and moving obstacles, using Velocity Obstacles (VO), for on-line planning in dynamic environments. Each obstacle is mapped to forbidden states by selecting a proper time horizon for the velocity obstacle. The proper choice of the time horizon ensures that the boundary of the mapped obstacle overlaps with the boundary of the set of inevitable collis...

متن کامل

Planning for Stochastic Games with Co-Safe Objectives

We consider planning problems for stochastic games with objectives specified by a branching-time logic, called probabilistic computation tree logic (PCTL). This problem has been shown to be undecidable if strategies with perfect recall, i.e., history-dependent, are considered. In this paper, we show that, if restricted to co-safe properties, a subset of PCTL properties capable to specify a wide...

متن کامل

Inevitable collision states. A step towards safer robots?

An inevitable collision state for a robotic system can be defined as a state for which, no matter what the future trajectory followed by the system is, a collision with an obstacle eventually occurs. An inevitable collision state takes into account the dynamics of both the system and the obstacles, fixed or moving. The main contribution of this paper is to lay down and explore this novel concep...

متن کامل