Inevitable collision states. A step towards safer robots?

By Thierry Fraichard, Hajime Asama. IEEE/RJS International Conference on Intelligent RObots and Systems, 2003

470 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/64be486150521eddcf83ef356a0719d1ef65ceb8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Safe Exploration Algorithms for Reinforcement Learning Controllers (2018, background): “They can be seen as an equivalent in the generalized states space of the inevitable collision states introduced in [37], and as the supercritical states deﬁned in [30] for a deterministic MDP.”
Planning algorithms (2006, background): “For recent progress on characterizing Xric, see [357].”
Ethical Decision Making during Automated Vehicle Crashes (2014, background): “In response, Fraichard and Asama introduced the concept of an inevitable collision state for mobile robots, defined as “a state for which, no matter what the future trajectory of the system is, a collision with an obstacle eventually occurs” (24).”
Viability and predictive control for safe locomotion (2008, unknown): “For a humanoid robot, limitations in its ability to keep its balance [17], for a wheeled robot, limitations in its ability to avoid tipping over during aggressive maneuvers on a rough terrain [13], [16], or more simply limitations in its ability to avoid obstacles [7], [4].”
Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation (2015, background): “A “probabilistic collision cost” is introduced (to assess the fitness of candidate robot trajectories in human crowds) that is based on the idea of inevitable collision states, described in Fraichard and Asama [37] and expanded in Bautin et al.”
Reciprocal n-Body Collision Avoidance (2011, background): “non-moving) [2, 4, 6, 7, 13, 14, 24], and compute an immediate action for the robot that would avert collisions with the obstacle, in many cases taking into account the robot’s kinematics and dynamics.”
Algorithms for collision-free navigation of mobile robots in complex cluttered environments: a survey (2014, background): “On the other side, approaches like velocity obstacles, 79 collision cones, 44 or inevitable collision states 85,207 assume a deterministic knowledge about the obstacle velocity and a moderate rate of its change.”
Toward Optimal Sampling in the Space of Paths (2007, background): “the lack of a solution may imply an inevitable collision [6] [10] so safety can be a valid concern.”
Sampling-Based Robot Motion Planning: A Review (2014, background): “Another subdivision exist in the free state space, referred to as Inevitable Collision States (ICS), in which the robot will collide with obstacles regardless of the control input applied [183].”
A survey on motion prediction and risk assessment for intelligent vehicles (2014, background): “This concept is closely related to the notion of Inevitable Collision States (ICS) [62] used in robotics.”
Human-robot collaborative manipulation planning using early prediction of human motion (2013, background): “In the closely-related topic of robot navigation in the presence of humans, early works were inspired by the social behavior demonstrated by humans [9].”
Reciprocal collision avoidance with acceleration-velocity obstacles (2011, methodology): “The works of [2], [7] are related to inevitable collision states [4], and define velocities as forbidden if no escape maneuver exists given the acceleration constraints to avoid collisions.”
Safety in human-robot collaborative manufacturing environments: Metrics and control (2016, background): “A similar concept has been also presented in [15], as well as with the so-called inevitable collision states presented in [16].”
Bayesian Learning for Safe High-Speed Navigation in Unknown Environments (2015, background): “A large body of work has established techniques for safe planning in static and dynamic environments [3, 8, 9, 25].”