An official website of the United States government
Abstract Human–exoskeleton interactions have the potential to bring about changes in human behavior for physical rehabilitation or skill augmentation. Despite significant advances in the design and control of these robots, their application to human training remains limited. The key obstacles to the design of such training paradigms are the prediction of human–exoskeleton interaction effects and the selection of interaction control to affect human behavior. In this article, we present a method to elucidate behavioral changes in the human–exoskeleton system and identify expert behaviors correlated with a task goal. Specifically, we observe the joint coordinations of the robot, also referred to as kinematic coordination behaviors, that emerge from human–exoskeleton interaction during learning. We demonstrate the use of kinematic coordination behaviors with two task domains through a set of three human-subject studies. We find that participants (1) learn novel tasks within the exoskeleton environment, (2) demonstrate similarity of coordination during successful movements within participants, (3) learn to leverage these coordination behaviors to maximize success within participants, and (4) tend to converge to similar coordinations for a given task strategy across participants. At a high level, we identify task-specific joint coordinations that are used by different experts for a given task goal. These coordinations can be quantified by observing experts and the similarity to these coordinations can act as a measure of learning over the course of training for novices. The observed expert coordinations may further be used in the design of adaptive robot interactions aimed at teaching a participant the expert behaviors.
more »
« less
IDIL: Imitation Learning of Intent-Driven Expert Behavior
When faced with accomplishing a task, human experts exhibit intentional behavior. Their unique intents shape their plans and decisions, resulting in experts demonstrating diverse behaviors to accomplish the same task. Due to the uncertainties encountered in the real world and their bounded rationality, experts sometimes adjust their intents, which in turn influences their behaviors during task execution. This paper introduces IDIL, a novel imitation learning algorithm to mimic these diverse intent-driven behaviors of experts. Iteratively, our approach estimates expert intent from heterogeneous demonstrations and then uses it to learn an intent-aware model of their behavior. Unlike contemporary approaches, IDIL is capable of addressing sequential tasks with high-dimensional state representations, while sidestepping the complexities and drawbacks associated with adversarial training (a mainstay of related techniques). Our empirical results suggest that the models generated by IDIL either match or surpass those produced by recent imitation learning benchmarks in metrics of task performance. Moreover, as it creates a generative model, IDIL demonstrates superior performance in intent inference metrics, crucial for human-agent interactions, and aptly captures a broad spectrum of expert behaviors.
more »
« less
- Award ID(s):
- 2205454
- PAR ID:
- 10517593
- Publisher / Repository:
- International Foundation for Autonomous Agents and Multiagent Systems
- Date Published:
- Journal Name:
- Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems
- Volume:
- 23
- ISBN:
- 979-8-4007-0486-4
- Page Range / eLocation ID:
- 1673 to 1782
- Subject(s) / Keyword(s):
- Hierarchical Imitation Learning Human Modeling Intention Prediction
- Format(s):
- Medium: X
- Location:
- Auckland, New Zealand
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Relevance to proposal: This project evaluates the generalizability of real and synthetic training datasets which can be used to train model-free techniques for multi-agent applications. We evaluate different methods of generating training corpora and machine learning techniques including Behavior Cloning and Generative Adversarial Imitation Learning. Our results indicate that the utility-guided selection of representative scenarios to generate synthetic data can have significant improvements on model performance. Paper abstract: Crowd simulation, the study of the movement of multiple agents in complex environments, presents a unique application domain for machine learning. One challenge in crowd simulation is to imitate the movement of expert agents in highly dense crowds. An imitation model could substitute an expert agent if the model behaves as good as the expert. This will bring many exciting applications. However, we believe no prior studies have considered the critical question of how training data and training methods affect imitators when these models are applied to novel scenarios. In this work, a general imitation model is represented by applying either the Behavior Cloning (BC) training method or a more sophisticated Generative Adversarial Imitation Learning (GAIL) method, on three typical types of data domains: standard benchmarks for evaluating crowd models, random sampling of state-action pairs, and egocentric scenarios that capture local interactions. Simulated results suggest that (i) simpler training methods are overall better than more complex training methods, (ii) training samples with diverse agent-agent and agent-obstacle interactions are beneficial for reducing collisions when the trained models are applied to new scenarios. We additionally evaluated our models in their ability to imitate real world crowd trajectories observed from surveillance videos. Our findings indicate that models trained on representative scenarios generalize to new, unseen situations observed in real human crowds.more » « less
-
Shared autonomy enables robots to infer user intent and assist in accomplishing it. But when the user wants to do a new task that the robot does not know about, shared autonomy will hinder their performance by attempting to assist them with something that is not their intent. Our key idea is that the robot can detect when its repertoire of intents is insufficient to explain the user’s input, and give them back control. This then enables the robot to observe unhindered task execution, learn the new intent behind it, and add it to this repertoire. We demonstrate with both a case study and a user study that our proposed method maintains good performance when the human’s intent is in the robot’s repertoire, outperforms prior shared autonomy approaches when it isn’t, and successfully learns new skills, enabling efficient lifelong learning for confidence-based shared autonomy.more » « less
-
Prevalent imitation learning methods seek to produce behavior that matches or exceeds average human performance. This often prevents achieving expert-level or superhuman performance when identifying the better demonstrations to imitate is difficult. We instead assume demonstrations are of varying quality and seek to induce behavior that is unambiguously better (i.e., Pareto dominant or minimally subdominant) than all human demonstrations. Our minimum subdominance inverse optimal control training objective is primarily defined by high quality demonstrations; lower quality demonstrations, which are more easily dominated, are effectively ignored instead of degrading imitation. With increasing probability, our approach produces superhuman behavior incurring lower cost than demonstrations on the demonstrator’s unknown cost function{—}even if that cost function differs for each demonstration. We apply our approach on a computer cursor pointing task, producing behavior that is 78% superhuman, while minimizing demonstration suboptimality provides 50% superhuman behavior{—}and only 72% even after selective data cleaning.more » « less
-
Agent navigation has been a crucial task in today's service and automated factories. Many efforts are to set specific rules for agents in a certain scenario to regulate the agent's behaviors. However, not all situations could be in advance considered, which might lead to terrible performance in a real-world application. In this paper, we propose CrowdGAIL, a method to learn from expert behaviors as an instructing policy, can train most 'human-like' agents in navigation problems without manually setting any reward function or beforehand regulations. First, the proposed model structure is based on generative adversarial imitation learning (GAIL), which imitates how humans take actions and move toward the target to a maximum extent, and by comparison, we prove the advantage of proximal policy optimization (PPO) to trust region policy optimization, thus, GAIL-PPO is what we base. Second, we design a special Sequential DemoBuffer compatible with the inner long short-term memory structure to apply spatiotemporal instruction on the agent's next step. Third, the paper demonstrates the potential of the model with an integrated social manner in a multi-agent scenario by considering human collision avoidance as well as social comfort distance. At last, experiments on the generated dataset from CrowdNav verify how close our model would act like a human being in the trajectory aspect and also how it could guide the multi-agents by avoiding any collision. Under the same evaluation metrics, CrowdGAIL shows better results compared with classic Social-GAN.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
