Robot Risk-Awareness by Formal Risk Reasoning and Planning

Abstract

This paper proposes a formal robot motion risk reasoning framework and develops a risk-aware path planner that minimizes the proposed risk. While robots locomoting in unstructured or confined environments face a variety of risk, existing risk only focuses on collision with obstacles. Such risk is currently only addressed in ad hoc manners. Without a formal definition, ill-supported properties, e.g. additive or Markovian, are simply assumed. Relied on an incomplete and inaccurate representation of risk, risk-aware planners use ad hoc risk functions or chance constraints to minimize risk. The former inevitably has low fidelity when modeling risk, while the latter conservatively generates feasible path within a probability bound. Using propositional logic and probability theory, the proposed motion risk reasoning framework is formal. Building upon a universe of risk elements of interest, three major risk categories, i.e. locale-, action-, and traverse-dependent, are introduced. A risk-aware planner is also developed to plan minimum risk path based on the newly proposed risk framework. Results of the risk reasoning and planning are validated in physical experiments in real-world unstructured or confined environments. With the proposed fundamental risk reasoning framework, safety of robot locomotion could be explicitly reasoned, quantified, and compared. The risk-aware planner finds safe path in terms of the newly proposed risk framework and enables more risk-aware robot behavior in unstructured or confined environments.

Best Viewpoints for External Robots or Sensors Assisting Other Robots

“…While beyond the scope of this dissertation, it is expected the model will reduce the cognitive workload on the primary robot operator. The model will enable to make the robotic visual assistant autonomous eliminating the need for the primary robot operator to manually control the robotic visual assistant or to coordinate with a secondary operator [21,22,23,24,25,26,27,28,29,30].…”

“…In [25,26] a formal robot motion risk reasoning framework was proposed enabling to quantify locale-dependent, action-dependent, and traversedependent risk for the robotic visual assistant. In [27,28,29,30] a risk-aware reward maximizing path planner was proposed that enables to simultaneously select a viewpoint and plan a path there while balancing the value of that viewpoint, the value of viewpoints along the path, and the associated locale-dependent, action-dependent, and traverse-dependent risk. The model of viewpoint values will supply the needed cost function quantifying the reward for the path planner.…”

Fast-Reactive Probabilistic Motion Planning for High-Dimensional Robots

“…Existing motion planners that take uncertainties into consideration include two classes: some are safety-driven and provide motion plans that minimize the collision risks [57,58,70,73], and others, also called chance-constrained motion planners [48], seek the optimal plans that can satisfy a userspecified constraint over the probability of collision. In this paper, we focus on providing chance-constrained motion plans for high-dimensional robots in real time.…”

DORA: Distributed Online Risk-Aware Explorer

“…Several path planners based on Markov Decision Processes [18], [19], [20] take into account risk and have useful definitions of it. However, they assume a knowledge of the global state of the environment, which is unavailable when exploring unknown environments.…”