An official website of the United States government
Goal-conditioned policies, such as those learned via imitation learning, provide an easy way for humans to influence what tasks robots accomplish. However, these robot policies are not guaranteed to execute safely or to succeed when faced with out-of-distribution goal requests. In this work, we enable robots to know when they can confidently execute a user’s desired goal, and automatically suggest safe alternatives when they cannot. Our approach is inspired by control-theoretic safety filtering, wherein a safety filter minimally adjusts a robot’s candidate action to be safe. Our key idea is to pose alternative suggestion as a safe control problem in goal space, rather than in action space. Offline, we use reachability analysis to compute a goal-parameterized reach-avoid value network which quantifies the safety and liveness of the robot’s pre- trained policy. Online, our robot uses the reach-avoid value network as a safety filter, monitoring the human’s given goal and actively suggesting alternatives that are similar but meet the safety specification. We demonstrate our Safe ALTernatives (SALT) framework in simulation experiments with indoor navigation and Franka Panda tabletop manipulation, and with both discrete and continuous goal representations. We find that SALT is able to learn to predict successful and failed closed-loop executions, is a less pessimistic monitor than open- loop uncertainty quantification, and proposes alternatives that consistently align with those that people find acceptable.
more »
« less
Planning to chronicle: Optimal policies for narrative observation of unpredictable events
One important class of applications entails a robot scrutinizing, monitoring, or recording the evolution of an uncertain time-extended process. This sort of situation leads to an interesting family of active perception problems that can be cast as planning problems in which the robot is limited in what it sees and must, thus, choose what to pay attention to. The distinguishing characteristic of this setting is that the robot has influence over what it captures via its sensors, but exercises no causal authority over the process evolving in the world. As such, the robot’s objective is to observe the underlying process and to produce a “chronicle” of occurrent events, subject to a goal specification of the sorts of event sequences that may be of interest. This paper examines variants of such problems in which the robot aims to collect sets of observations to meet a rich specification of their sequential structure. We study this class of problems by modeling a stochastic process via a variant of a hidden Markov model and specify the event sequences of interest as a regular language, developing a vocabulary of “mutators” that enable sophisticated requirements to be expressed. Under different suppositions on the information gleaned about the event model, we formulate and solve different planning problems. The core underlying idea is the construction of a product between the event model and a specification automaton. Using this product, we compute a policy that minimizes the expected number of steps to reach a goal state. We introduce a general algorithm for this problem as well as several more efficient algorithms for important special cases. The paper reports and compares performance metrics by drawing on some small case studies analyzed in depth via simulation. Specifically, we study the effect of the robot’s observation model on the average time required for the robot to record a desired story. We also compare our algorithm with a baseline greedy algorithm, showing that our algorithm outperforms the greedy algorithm in terms of the average time to record a desired story. In addition, experiments show that the algorithms tailored to specialized variants of the problem are rather more efficient than the general algorithm.
more »
« less
- PAR ID:
- 10364526
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- The International Journal of Robotics Research
- ISSN:
- 0278-3649
- Page Range / eLocation ID:
- Article No. 027836492110691
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We consider the problem of deploying robots to observe the evolution of a stochastic process in order to output a sequence of observations that fit some given specification. This problem often arises in contexts such as event reporting, situation depiction, and automated narrative generation. The paper extends our prior work by formulating and examining the multi-robot case: a team of robots move about, each recording what they observe, and, if they manage to capture some event, communicating that fact with the group. In the end, all events from all the robots are collated to provide a cumulative output. A plan is used to decide what each robot will attempt to capture next, based on the state of the world and the events that have been captured (collectively) so far. This paper focuses on the question of how to compute effective multi-robot plans. A monolithic treatment, involving the optimal selection of joint choices, i.e., choosing the next elements to attempt to capture by all robots, is formulated where costs are minimized in an expected sense. Since such plans are prohibitive to compute, variants based on an approximation scheme based on solving a sequence of individual planning problems are then introduced. This scheme sacrifices some solution quality but requires far less computational expense; we show this permits one to scale to greater numbers of robots.more » « less
-
Soft robots have shown great potential to enable safe interactions with unknown environments due to their inherent compliance and variable stiffness. However, without knowledge of potential contacts, a soft robot could exhibit rigid behaviors in a goal-reaching task and collide into obstacles. In this paper, we introduce a Sliding Mode Augmented by Reactive Transitioning (SMART) controller to detect the contact events, adjust the robot’s desired trajectory, and reject estimated disturbances in a goal reaching task. We employ a sliding mode controller to track the desired trajectory with a nonlinear disturbance observer (NDOB) to estimate the lumped disturbance, and a switching algorithm to adjust the desired robot trajectories. The proposed controller is validated on a pneumatic-driven fabric soft robot whose dynamics is described by a new extended rigid-arm model to fit the actuator design. A stability analysis of the proposed controller is also presented. Experimental results show that, despite modeling uncertainties, the robot can detect obstacles, adjust the reference trajectories to maintain compliance, and recover to track the original desired path once the obstacle is removed. Without force sensors, the proposed model-based controller can adjust the robot’s stiffness based on the estimated disturbance to achieve goal reaching and compliant interaction with unknown obstacles.more » « less
-
Narrative planning generates a sequence of actions which must achieve the author's goal for the story and must be composed only of actions that make sense for the characters who take them. A causally necessary action is one that would make the plan impossible to execute if it were left out. We hypothesize that action sequences which are solutions to narrative planning problems are more likely to feature causally necessary actions than those which are not solutions. In this paper, we show that prioritizing sequences with more causally necessary actions can lead to solutions faster in ten benchmark story planning problems.more » « less
-
We consider a class of robotic systems composed of high-elongation linear actuators connected at universal joints. We derive the differential kinematics of such robots, and show that any instantaneous velocity of the nodes can be achieved through actuator motions if the graph describing the robot’s configuration is infinitesimally rigid. We formulate physical constraints that constrain the maximum and minimum length of each actuator, the minimum distance between unconnected actuators, the minimum angle between connected actuators, and constraints that ensure the robot avoids singular configurations. We present two planning algorithms that allow a linear actuator robot to locomote. The first algorithm repeatedly solves a nonlinear optimization problem online to move the robot’s center of mass in a desired direction for one time step. This algorithm can be used for an arbitrary linear actuator robot but does not guarantee persistent feasibility. The second method ensures persistent feasibility with a hierarchical coarse-fine planning decomposition, and applies to linear actuator robots with a certain symmetry property. We compare these two planning methods in simulation studies.more » « less
