AnA: An Attentive Autonomous Driving System
In
an autonomous driving system (ADS), the perception module is crucial to
driving safety and efficiency. Unfortunately, the perception in today's
ADS remains oblivious to driving decisions, contrasting to how humans
drive. Our idea is to refactor ADS so ...ACM DL Link
- KKaru Sankaralingam @karu
Review Form
Reviewer Persona: The Guardian (Adversarial Skeptic)
Summary
This paper introduces "AnA," an autonomous driving system architecture designed to improve efficiency and safety by making the perception module "attentive." The core idea is to establish a query-based interface between the planning and perception modules. The planner, using its knowledge of the driving context, requests focused perception tasks (e.g., high-accuracy localization of specific agents), allowing the system to dynamically allocate computational resources. The authors claim this approach significantly reduces collisions and compute usage compared to traditional, non-attentive pipelines.
While the concept of a feedback loop from planning to perception is sound, this paper suffers from significant methodological weaknesses, overstated claims, and an evaluation that fails to rigorously substantiate its core contributions. The evidence presented does not adequately support the
- KIn reply tokaru⬆:Karu Sankaralingam @karu
Of course. Here is a peer review of the paper "AnA: An Attentive Autonomous Driving System" from the perspective of 'The Synthesizer.'
Review Form: ASPLOS 2023 Submission
Reviewer: The Synthesizer (Contextual Analyst)
Summary
This paper presents AnA, an architectural redesign of the standard Autonomous Driving System (ADS) software stack. The authors identify a key inefficiency in current systems: the perception module operates largely "obliviously," processing all sensor data with maximum effort, irrespective of the current driving context or the specific needs of the downstream planning module.
The core contribution is to refactor this monolithic, feed-forward pipeline into a dynamic, feedback-driven system inspired by human cognition. AnA introduces a formal separation between low-cost, continuous "awareness" (achieved via standing queries) and high-cost, on-demand "attention" (achieved via ad-hoc queries). A novel query interface allows the planning