Sense–Assess–eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios

Gadd, Matthew; Martini, Daniele De; Marchegiani, Letizia; Newman, Paul; Kunze, Lars

doi:10.1109/iv47402.2020.9304819

Cited by 13 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Sense Access eXplain (SAX) project 4 in the Oxford Robotics Institute (ORI) is currently collecting driving data which includes some proprioception information from the CAN bus of a Jaguar Land Rover (JLR) ego vehicle [188]. Some of the relevant CAN bus data include wheel angle, yaw, acceleration, and braking, among others.…”

Section: A Standards and Regulationsmentioning

confidence: 99%

Explanations in Autonomous Driving: A Survey

Omeiza

Webb

Jirotka

et al. 2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

143

View full text Add to dashboard Cite

The automotive industry has witnessed an increasing level of development in the past decades; from manufacturing manually operated vehicles to manufacturing vehicles with a high level of automation. With the recent developments in Artificial Intelligence (AI), automotive companies now employ blackbox AI models to enable vehicles to perceive their environments and make driving decisions with little or no input from a human. With the hope to deploy autonomous vehicles (AV) on a commercial scale, the acceptance of AV by society becomes paramount and may largely depend on their degree of transparency, trustworthiness, and compliance with regulations. The assessment of the compliance of AVs to these acceptance requirements can be facilitated through the provision of explanations for AVs' behaviour. Explainability is therefore seen as an important requirement for AVs. AVs should be able to explain what they have 'seen', done, and might do in environments in which they operate.In this paper, we provide a comprehensive survey of the existing body of work around explainable autonomous driving. First, we open with a motivation for explanations by highlighting and emphasising the importance of transparency, accountability, and trust in AVs; and examining existing regulations and standards related to AVs. Second, we identify and categorise the different stakeholders involved in the development, use, and regulation of AVs and elicit their explanation requirements for AV. Third, we provide a rigorous review of previous work on explanations for the different AV operations (i.e., perception, localisation, planning, control, and system management). Finally, we identify pertinent challenges and provide recommendations, such as a conceptual framework for AV explainability. This survey aims to provide the fundamental knowledge required of researchers who are interested in explainability in AVs.

show abstract

Section: A Standards and Regulationsmentioning

confidence: 99%

Explanations in Autonomous Driving: A Survey

Omeiza

Webb

Jirotka

et al. 2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

143

View full text Add to dashboard Cite

show abstract

“…The use of scene graphs allows for explainable intermediate representation of driving scenes. As a further step, interpretbility and intelligibility need to be considered all through the learning and prediction process in order to enhance transparency and accountability [16]. Hence, we apply interpretable models (tree-based) with high intelligibility (natural language explanation) in risk prediction and classification tasks.…”

Section: B Explanations In Risk Assessmentmentioning

confidence: 99%

Assessing and Explaining Collision Risk in Dynamic Environments for Autonomous Driving Safety

Nahata

Omeiza

Howard

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Autonomous vehicles operating in dynamic environments are required to account for other traffic participants. By interpreting sensor information and assessing the collision risk with vehicles, cyclists, and pedestrians, near-misses and accidents can be prevented. Moreover, by explaining risk factors to developers and engineers the overall safety of autonomous driving can be increased in future deployments.In this paper, we have designed, developed, and evaluated an approach for predicting the collision risk with other road users based on a planar 2D collision model. To this end, we have trained interpretable machine learning models to classify and predict the risk of collisions on a range of features extracted from sensor data. Further, we present methods for inferring and explaining the factors mostly contributing to the risk. Using counterfactual inference, our approach allows us to determine the factors which highly influence the risk and should in turn be minimised. Experimental results on real-world driving data show that collision risk can be effectively predicted and explained for different time horizons as well as different types of traffic participants such as cars, cyclists and pedestrians.

show abstract

“…Further, to the extent that our predictions are structured around the interpretation of observed trajectories in terms of high-level maneuvers, the goal recognition process lends itself to intuitive interpretation for the purposes of system analysis and debugging, at a level of detail suggested in Figure 2. As we develop towards making our autonomous systems more trustworthy [21], these notions of interpretation and the ability to justify (explain) the system's decisions are key [22].…”

Section: Introductionmentioning

confidence: 99%

Interpretable Goal-based Prediction and Planning for Autonomous Driving

Albrecht

Brewitt

Wilhelm

et al. 2021

2021 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We propose an integrated prediction and planning system for autonomous driving which uses rational inverse planning to recognise the goals of other vehicles. Goal recognition informs a Monte Carlo Tree Search (MCTS) algorithm to plan optimal maneuvers for the ego vehicle. Inverse planning and MCTS utilise a shared set of defined maneuvers and macro actions to construct plans which are explainable by means of rationality principles. Evaluation in simulations of urban driving scenarios demonstrate the system's ability to robustly recognise the goals of other vehicles, enabling our vehicle to exploit non-trivial opportunities to significantly reduce driving times. In each scenario, we extract intuitive explanations for the predictions which justify the system's decisions.• A method for goal recognition and multi-modal trajectory prediction via rational inverse planning.

show abstract

Sense–Assess–eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios

Cited by 13 publications

References 38 publications

Explanations in Autonomous Driving: A Survey

Explanations in Autonomous Driving: A Survey

Assessing and Explaining Collision Risk in Dynamic Environments for Autonomous Driving Safety

Interpretable Goal-based Prediction and Planning for Autonomous Driving

Contact Info

Product

Resources

About