CausalMind汇流知行
← All data types

04 / RSI / IOT TASK BENCH

RSI-IoT algorithm research tasks

RSI Task Bench turns real perception data into trainable and evaluable environments for algorithm-research agents.

IMU time seriesImage & depthRadar detection5-shot speech
WHAT IT IS

The current scope is RSI-IoT. IMU time series, images, radar, depth data, and speech features are organized into tasks with explicit data boundaries, resource limits, and acceptance checks. Within a fixed compute and time budget, an agent analyzes data, designs a method, validates it experimentally, and submits a runnable solution rather than a written proposal alone.

RSI TASK BENCH / IOT

Perception tasks in scope

Six task forms spanning time series, vision, radar, depth, and speech.

  1. 01

    IMU activity recognition

    Build a reproducible classifier from time-series windows and activity labels.

  2. 02

    Cross-client generalization

    Hold out clients to test transfer across devices and participants.

  3. 03

    Multimodal few-shot learning

    Combine limited labeled examples from several perception modalities.

  4. 04

    Infant-monitor image classification

    Classify authorized monitor images under a defined label set.

  5. 05

    Radar and image person detection

    Design a detector and validate predictions against held-out scenes.

  6. 06

    5-shot spoken commands

    Adapt a speech-command recognizer from five examples per class.

TASK-APPROPRIATE FEEDBACKMacro F1Mean cross-client accuracyAP50

DELIVERY / CONTENT

What a delivery can include

Defined with each project and its authorization scope.

  1. 01Harbor isolated environment, public development data, and a separate hidden test set
  2. 02Task brief, unified inference entry point, experiment logs, and runnable solution
  3. 03Public scorer and independent automated evaluator, with task-appropriate Macro F1, mean cross-client accuracy, or AP50 feedback

SCENARIO / EXAMPLE

A task in context

For cross-client IMU activity recognition, an agent examines class and client differences in public development data, trains a model, and submits through a unified inference entry point. Held-out clients remain reserved for independent evaluation.

QUALITY SIGNAL / 04

What we verify

Check task-appropriate Macro F1, mean cross-client accuracy, or AP50, plus time and compute limits, data separation, executable inference, and reproducibility.

CONTEXT→ACTION→FEEDBACK