اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدQuantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections
98
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the humans desired objective already exists within the robots hypothesis space. In reality, this assumption is often inaccurate: there will always be situations where the person might care about aspects of the task that the robot does not know about. Without this knowledge, the robot cannot infer the correct objective. Hence, when the robots hypothesis space is misspecified, even methods that keep track of uncertainty over the objective fail because they reason about which hypothesis might be correct, and not whether any of the hypotheses are correct. In this paper, we posit that the robot should reason explicitly about how well it can explain human inputs given its hypothesis space and use that situational confidence to inform how it should incorporate human input. We demonstrate our method on a 7 degree-of-freedom robot manipulator in learning from two important types of human input: demonstrations of manipulation tasks, and physical corrections during the robots task execution.
قيم البحث
اقرأ أيضاً
Imitating human demonstrations is a promising approach to endow robots with various manipulation capabilities. While recent advances have been made in imitation learning and batch (offline) reinforcement learning, a lack of open-source human datasets
and reproducible learning methods make assessing the state of the field difficult. In this paper, we conduct an extensive study of six offline learning algorithms for robot manipulation on five simulated and three real-world multi-stage manipulation tasks of varying complexity, and with datasets of varying quality. Our study analyzes the most critical challenges when learning from offline human data for manipulation. Based on the study, we derive a series of lessons including the sensitivity to different algorithmic design choices, the dependence on the quality of the demonstrations, and the variability based on the stopping criteria due to the different objectives in training and evaluation. We also highlight opportunities for learning from human datasets, such as the ability to learn proficient policies on challenging, multi-stage tasks beyond the scope of current reinforcement learning methods, and the ability to easily scale to natural, real-world manipulation scenarios where only raw sensory signals are available. We have open-sourced our datasets and all algorithm implementations to facilitate future research and fair comparisons in learning from human demonstration data. Codebase, datasets, trained models, and more available at https://arise-initiative.github.io/robomimic-web/
When a robot performs a task next to a human, physical interaction is inevitable: the human might push, pull, twist, or guide the robot. The state-of-the-art treats these interactions as disturbances that the robot should reject or avoid. At best, th
ese robots respond safely while the human interacts; but after the human lets go, these robots simply return to their original behavior. We recognize that physical human-robot interaction (pHRI) is often intentional -- the human intervenes on purpose because the robot is not doing the task correctly. In this paper, we argue that when pHRI is intentional it is also informative: the robot can leverage interactions to learn how it should complete the rest of its current task even after the person lets go. We formalize pHRI as a dynamical system, where the human has in mind an objective function they want the robot to optimize, but the robot does not get direct access to the parameters of this objective -- they are internal to the human. Within our proposed framework human interactions become observations about the true objective. We introduce approximations to learn from and respond to pHRI in real-time. We recognize that not all human corrections are perfect: often users interact with the robot noisily, and so we improve the efficiency of robot learning from pHRI by reducing unintended learning. Finally, we conduct simulations and user studies on a robotic manipulator to compare our proposed approach to the state-of-the-art. Our results indicate that learning from pHRI leads to better task performance and improved human satisfaction.
Teaching an anthropomorphic robot from human example offers the opportunity to impart humanlike qualities on its movement. In this work we present a reinforcement learning based method for teaching a real world bipedal robot to perform movements dire
ctly from human motion capture data. Our method seamlessly transitions from training in a simulation environment to executing on a physical robot without requiring any real world training iterations or offline steps. To overcome the disparity in joint configurations between the robot and the motion capture actor, our method incorporates motion re-targeting into the training process. Domain randomization techniques are used to compensate for the differences between the simulated and physical systems. We demonstrate our method on an internally developed humanoid robot with movements ranging from a dynamic walk cycle to complex balancing and waving. Our controller preserves the style imparted by the motion capture data and exhibits graceful failure modes resulting in safe operation for the robot. This work was performed for research purposes only.
Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that generalize beyond t
he demonstrated behaviors is still an open challenge. We present a novel imitation learning framework to enable robots to 1) learn complex real world manipulation tasks efficiently from a small number of human demonstrations, and 2) synthesize new behaviors not contained in the collected demonstrations. Our key insight is that multi-task domains often present a latent structure, where demonstrated trajectories for different tasks intersect at common regions of the state space. We present Generalization Through Imitation (GTI), a two-stage offline imitation learning algorithm that exploits this intersecting structure to train goal-directed policies that generalize to unseen start and goal state combinations. In the first stage of GTI, we train a stochastic policy that leverages trajectory intersections to have the capacity to compose behaviors from different demonstration trajectories together. In the second stage of GTI, we collect a small set of rollouts from the unconditioned stochastic policy of the first stage, and train a goal-directed agent to generalize to novel start and goal configurations. We validate GTI in both simulated domains and a challenging long-horizon robotic manipulation domain in the real world. Additional results and videos are available at https://sites.google.com/view/gti2020/ .
When the human-robot interactions become ubiquitous, the environment surrounding these interactions will have significant impact on the safety and comfort of the human and the effectiveness and efficiency of the robot. Although most robots are design
ed to work in the spaces created for humans, many environments, such as living rooms and offices, can be and should be redesigned to enhance and improve human-robot collaboration and interactions. This work uses autonomous wheelchair as an example and investigates the computational design in the human-robot coexistence spaces. Given the room size and the objects $O$ in the room, the proposed framework computes the optimal layouts of $O$ that satisfy both human preferences and navigation constraints of the wheelchair. The key enabling technique is a motion planner that can efficiently evaluate hundreds of similar motion planning problems. Our implementation shows that the proposed framework can produce a design around three to five minutes on average comparing to 10 to 20 minutes without the proposed motion planner. Our results also show that the proposed method produces reasonable designs even for tight spaces and for users with different preferences.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
