top of page (8).gif

Ad-hoc Human-Robot Swarms
What's the Best Robot Strategy to Evacuate Humans?

What strategy should a robot take to lead humans out of a building during an emergency? Specifically, how should the robot act when evacuees are motivated to stay back and pick up valuable items, delaying their evacuation? We present a study in a simulated environment that compares an actively nudging robot strategy, where the robot keeps pulling the human toward the exit, to a passive one, where the robot waits for the human to activate the evacuation when they are ready.

Who should lead the evacuation in a time of emergency?  On the one hand, humans may panic, prioritize valuables, and delay responses under stressful evacuation scenarios, whereas robots could be more rational in evaluating risks and planning a safe path. On the other hand, robots may not be able to sense essential considerations, such as the presence of victims and the user’s emotional state.

Based on this dilemma, we developed two robot strategies: Under the nudging strategy, the robot takes the lead and constantly nudges the human toward the exit. Under the waiting strategy, the user decides when and where to go, and the robot provides help when requested.


Nudging Robot

Waiting Robot

To study this question, we set up a simulated environment in the unity game engine where participants have to evacuate a building within three minutes while being guided by a robot. Participants have two conflicting incentives: picking up valuable items and exiting the building. This is to simulate noncompliance based on the fact that people often delay evacuation due to them gathering valuables. We run a within-participant design, where each participant experiences two robot strategies, nudging and waiting. The robots are autonomous; their control was automatically synthesized from high-level specifications.

Screen Shot 2022-09-13 at 1.01.23 PM.png
Screen Shot 2023-02-08 at 4.16.18 PM.png

We applied mixed methods to the data, including both quantitative and qualitative analysis. We found a strong order effect on many of our dependent variables. Round 1 had a much lower success rate (10%) compared to Round 2 (85%). Participants rated their Satisfaction, Evacuation Prioritization, robot usage Easiness, and Clarity much higher and  pressed the evacuation command noticeably sooner in Round 2

Screen Shot 2023-02-08 at 8.42.53 PM.png

To better understand the attitudes towards the robots while controlling for the strong order effects, we ran independent 𝑡-tests between nudging and waiting robots, separately for Round 1 and Round 2. In Round 1, nudging robots were rated higher than waiting robots on Helpfulness, Trust, Clarity, Easiness, and less Conflict. Interestingly, in Round 2, participants perceived the waiting robot equally or slightly better than the nudging robot on those scales

The video plots participants' trajectories of the two rounds. In Round 1, participants with a nudging robot started off moving faster toward the exit, and this trend continued until the end of the game.  Although 90% of the participants failed the evacuation, participants guided by the nudging robot ended up closer to the
exit than those guided by the waiting robot.

In Round 2, participants led by the nudging
robot got ahead of the waiting robots at the beginning. However, the waiting group caught up with the nudging group after 𝑡 = 120𝑠.

We provide several design implications according to our quantitative and qualitative analysis:

(1) Nudging is Useful in an Unfamiliar Setting

We found in Round 1, the nudging robot strategy was especially useful for encouraging participants to evacuate as soon as possible and decreasing their mental loads. This indicates that giving users more control authority is not always beneficial, especially when users are in a new situation and stressed.

(2) Experts Need Less Nudging

The improvement in Round 2 for waiting robots shows that when participants have more knowledge of the task, robots, and environments, they are more comfortable taking control authority, making important decisions (e.g., when to evacuate), and choosing preferences of the robot’s behaviors (e.g., staying in front of or behind the user).

(3) Stay Close By but Don’t Interfere

An important variable that has affected evacuation effectiveness is the distance the robot stays from the user. While a close-staying robot may increase the sense of security and its likability, a distant robot may provide pressure for participants to catch up, thus encouraging evacuation.

Screen Shot 2023-02-09 at 7.17.52 PM.png

(5) Pay Attention to External and Affective Signals.

Besides the robot behavior, environmental signals and emotional state could also affect users’ compliance level. A robot would have to monitor environmental signals such as smoke, noise level, and evacuation signage to account for users’ behaviors and provide
the best assistance. The design of an evacuation robot should also carefully deal with users’ emotions by monitoring their stress levels and developing different strategies to calm them and develop trust.

Screen Shot 2023-02-09 at 7.17.44 PM.png

(4) Good Information Display Design is Critical.

It is crucial to carefully design the information display of an emergency evacuation robot, such as by displaying the evacuation route and estimated time toward an exit as supporting proof. Having too much information requires time and effort for users to process, causing inefficiency and stress. Given the variances between participants’ preferences, another idea is to customize the display based on participants’ movements and emotions.


Hu, Yuhan, , et al. “Nudging or Waiting? Automatically Synthesized Robot Strategies for Evacuating Noncompliant Users in an Emergency Situation.” In Proceedings of the 2023 ACM/IEEE International Conference on Human‑Robot Interaction (HRI ’23)

bottom of page