When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI

Sihan Jia; Oliver Lemon

cs.AIAug 28, 2026

When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI

Authors: Sihan Jia, Oliver Lemon

Organizations: School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, United Kingdom

Abstract

We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them preserve semantic structure but increase harmful ambiguity, while others weaken the model refusal behaviour and allow unsafe plans to be generated and executed. We show that in some cases automatic correction of ASR errors can reduce the risk, but this is not always effective. Overall, we show that ASR errors lead to significant safety risks for embodied AI.

Figures & tables

Figure 1: Example unsafe executable policy induced by POEX adversarial suffixes ( Lu et al., 2024 ) .

Figure 2: Overall Research Design and Information Flow.

Figure 3: Examples of four ASR Error Types.

Figure 4: Examples of noise at different WER levels.

Error Type	AR (%)	ESR (%)	Safety Flips
Baseline (Clean)	55.33	35.33	—
Acoustic Substitution	60.00	38.67	14
Grammar Confusion	51.33	32.00	5
Punctuation Segmentation	52.00	30.67	11
Short Word Omission/Substitution	54.00	38.00	8
Noise Addition (Mild, WER 6%)	56.00	33.33	8

Table 1: Safety evaluation results under different ASR error types (for Qwen2.5-7B-Instruct)

Error Type	AR	ESR	Flips
Baseline (Clean)	55.33	35.33	—
Acoustic Substitution	60.00	38.67	14
Heavy Noise (WER 53%)	62.00	36.00	14
Acoustic Substitution (Corr.)	53.33	30.67	6
Heavy Noise (Corr.)	57.33	36.00	13

Table 2: POEX Correction Results

Cond.	Model	Eval.	Success	Fail	Rate
Clean	GPT-4o-mini	300	83	217	27.67%
Clean	GPT-4.1-mini	300	114	186	38.00%
Mixed ASR	GPT-4o-mini	300	70	230	23.33%
Mixed ASR	GPT-4.1-mini	300	107	193	35.67%

Table 3: SafeAgentBench Results Under Clean and Mixed ASR Conditions

AI Agent Safety

AI agent safety studies how to prevent and detect harmful actions by autonomous systems that use tools, memory, and multi-step plans.

See all 330 papers

Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI
Oct 5, 2026Christopher Leet, Achu Menon, Sravanthi Machcha +12Robot Safety AI Agent Evaluation
Robocurve · University of Southern California · San Jose State University +7
GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI
Aug 22, 2026Zhesheng Zhang, Jiahao Lu, Wei Liu +8AI Safety Evaluation AI Safety
Shandong University · National University of Singapore · Nanjing University of Aeronautics and Astronautics +2
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Apr 21, 2026Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5Safety Evaluation of VLA Models LLM Safety Benchmarks
University of Michigan · Boise State University

Oct 5, 2026J/K move · Enter open · S save

Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI

Christopher Leet, Achu Menon, Sravanthi Machcha, Sabrina Zou+11

Robocurve · University of Southern California · San Jose State University+7

Robot Safety AI Agent Evaluation Robotic Policy Evaluation Embodied AI AI Safety Evaluation AI Agent Safety Benchmarks+1

Open paper AskPDF arXiv

General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodied is therefore increasingly important for understanding their societal impact and risks. To this end, we introduce Inspect Robots, a modular, open-source framework for developing and running evaluations of embodied agents. Inspect Robots pairs customizable, reusable abstractions for specifying physical evaluations and analyzing their results with infrastructure that automates evaluation setup, execution and termination. We demonstrate Inspect Robots by using it to evaluate the capabilities and safety of six policies based on frontier language models. Inspect Robots has seen significant early uptake, receiving nearly 100,000 downloads in the three months since its release.

Abstract

AI Agent Safety

Explore similar work

Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI

GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models