Monitoring and Diagnosability of Perception Systems

  title={Monitoring and Diagnosability of Perception Systems},
  author={Pasquale Antonante and David I. Spivak and Luca Carlone},
  journal={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving vehicles. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception systems, currently there is no formal approach for system-level monitoring. In this work, we propose a… 

Figures from this paper

LiDAR-Based GNSS Denied Localization for Autonomous Racing Cars
A localization architecture for a racing car that does not rely on Global Navigation Satellite Systems and consists of two multi-rate Extended Kalman Filters and an extension of a state-of-the-art laser-based Monte Carlo localization approach that exploits some a priori knowledge of the environment and context.
Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification
This paper formalizes the problem of runtime fault detection and identification in perception systems and presents a framework to model diagnostic information using a diagnostic graph, and provides a set of deterministic, probabilistic, and learning-based algorithms that use diagnostic graphs to perform fault detection.
A Review of Testing Object-Based Environment Perception for Safe Automated Driving
It is found that the realization of safety-oriented perception testing remains an open issue since challenges concerning the three testing axes and their interdependencies currently do not appear to be sufficiently solved.
Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems
This survey article analyzed how resilience is achieved in networks of agents and multirobot systems that are able to overcome adversity by leveraging system-wide complementarity, diversity, and redundancy—often involving a reconfiguration of robotic capabilities to provide some key ability that was not present in the system a priori.
Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
This paper attempts to identify trends emerging in the literature in the face of run-time monitoring of performance and reliability of perception systems and summarize the various approaches to the topic.


Formal Verification of Complex Robotic Systems on Resource-Constrained Platforms
This work proposes to use formal methods to check whether the tasks of a robotic application are schedulable with respect to a given hardware platform, and automatically translates functional components specified in GenoM into FIACRE, a formal language for timed systems.
Recent Trends in Formal Validation and Verification of Autonomous Robots Software
  • F. Ingrand
  • Computer Science
    2019 Third IEEE International Conference on Robotic Computing (IRC)
  • 2019
This work proposes to consider the overall problem of V&V of autonomous systems software and examines the current situation with respect to the various type of software used, pointing out that the availability of formal models is rather different depending on the type of component considered.
Challenges in Autonomous Vehicle Testing and Validation
Five major challenge areas in testing according to the V model for autonomous vehicles are identified: driver out of the loop, complex requirements, non-deterministic algorithms, inductive learning algorithms, and failoperational systems.
Self-Driving Vehicle Verification Towards a Benchmark
This paper presents a simple formal model for self-deriving cars and hopes this serves as a challenge problem for formal verification tools targeting industrial applications.
An 0(n2.5) Fault Identification Algorithm for Diagnosable Systems
It is shown that tp-diagnosable systems, due to their robust interconnection structure, possess heretofore unknown graph theoretic properties relative to vertex cover sets and maximum matchings.
On the Connection Assignment Problem of Diagnosable Systems
This paper treats the problem of automatic fault diagnosis for systems with multiple faults by means of a given arrangement of testing links (connection assignment), and a proper diagnosis can be arrived at for any diagnosable fault pattern.
An O(t3 + |E|) Fault Identification Algorithm for Diagnosable Systems
An algorithm is presented that performs this type of diagnosis for the system-level fault model with tight time bound when the total number of system components n is small and this is the tightest known time bound.
On a Formal Model of Safe and Scalable Self-driving Cars
A white-box, interpretable, mathematical model for safety assurance, which the authors call-Sensitive Safety (RSS), and a design of a system that adheres to the safety assurance requirements and is scalable to millions of cars.
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
What is now the de-facto standard formulation for SLAM is presented, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers.
and R
  • T. Chien, “On the connection assignment problem of diagnosable systems,” IEEE Transactions on Electronic Computers, no. 6, pp. 848– 854
  • 1967