Robot Locomotion Group
Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-world testing is prohibitively expensive and unscalable. In this work, we employ a probabilistic approach to safety evaluation in simulation, where we are concerned with computing the probability of dangerous events. We develop a novel rare-event simulation method that combines exploration, exploitation, and optimization techniques to find failure modes and estimate their rate of occurrence. We provide rigorous guarantees for the performance of our method in terms of both statistical and computational efficiency. Finally, we demonstrate the efficacy of our approach on a variety of scenarios, illustrating its usefulness as a tool for rapid sensitivity analysis and model comparison that are essential to developing and testing safety-critical autonomous systems.
Under review. Comments welcome.
This paper presents a novel method, combining new formulations and sampling, to improve the scalability of sum-of-squares (SOS) programs-based system verification. Region-of-attraction approximation problems are considered for polynomial, polynomial with generalized Lure uncertainty, and rational trigonometric multi-rigid-body systems. Our method starts by identifying that Lagrange multipliers, traditionally heavily used for S-procedures, are a major culprit of creating bloated SOS programs. In light of this, we exploit inherent system properties such as continuity, convexity, and implicit algebraic structure, and reformulate the problems as quotient-ring SOS programs, thereby eliminating all the multipliers. These new programs are smaller, sparser, less constrained, yet less conservative. Their computation is further improved by leveraging a recent result on sampling algebraic varieties. Remarkably, solution correctness is guaranteed with just a finite (in practice, very small) number of samples. Altogether, the proposed method can verify systems well beyond the reach of existing SOS-based approaches (29 states); on smaller problems where a baseline is available, it computes tighter solution 2-3 orders faster. Source code is included.
Under review. Comments welcome.
In this paper, we tackle the problem of pushing piles of small objects into a desired target set using visual feedback. Unlike conventional single-object manipulation pipelines, which estimate the state of the system parametrized by pose, the underlying physical state of this system is difficult to observe from images. Thus, we take the approach of reasoning directly in the space of images, and acquire the dynamics of visual measurements in order to synthesize a visual-feedback policy. We present a simple controller using an image-space Lyapunov function, and evaluate the closed-loop performance using three different class of models for image prediction: deep-learning-based models for image-to-image translation, an object-centric model obtained from treating each pixel as a particle, and a switched-linear system where an action-dependent linear map is used. Through results in simulation and experiment, we show that for this task, a linear model works surprisingly well -- achieving better prediction error, downstream task performance, and generalization to new environments than the deep models we trained on the same amount of data. We believe these results provide an interesting example in the spectrum of models that are most useful for vision-based feedback in manipulation, considering both the quality of visual prediction, as well as compatibility with rigorous methods for control design and analysis.
Supplemental materials: https://www.youtube.com/watch?v=HfFSnsnR590
Under review. Comments welcome.
We propose a method to control linear time-varying (LTV) discrete-time systems subject to bounded process disturbances and measurable outputs with bounded noise, and polyhedral constraints over system inputs and states. We search over control policies that map the history of measurable outputs to the current control input. We solve the problem in two stages. First, using the original system, we build a linear system that predicts future observations using the past observations. The bounded errors are characterized using zonotopes. Next, we propose control laws based on affine maps of such output prediction errors, and show that controllers can be synthesized using convex linear/quadratic programs. Furthermore, we can add constraints on trajectories and guarantee their satisfaction for all allowable sequences of observation noise and process disturbances. Our method does not require any assumptions about system controllability and observability. The controller design does not directly take into account the state-space dynamics, and its implementation does not require an observer. Instead, partial observability is often sufficient to design a correct controller. We provide the polytopic representation of observability errors and reachable sets in the form of zonotopes. Illustrative examples are included.
To Appear at HSCC 2020. Comments welcome.
In hybrid Model Predictive Control (MPC), a Mixed-Integer Convex Program (MICP) is solved at each sampling time to compute the optimal control action. Although these optimizations are generally very demanding, in MPC we expect consecutive problem instances to be nearly identical. This paper addresses the question of how computations performed at one time step can be reused to accelerate ('warm start') the solution of subsequent MICPs. Reoptimization is not a rare practice in integer programming: for small variations of certain problem data, the branch-and-bound algorithm allows an efficient reuse of its search tree and the dual bounds of its leaf nodes. In this paper we extend these ideas to the receding-horizon settings of MPC. The warm-start algorithm we propose copes naturally with arbitrary model errors, has negligible computational cost, and frequently enables an a-priori pruning of most of the search space. Theoretical considerations and experimental evidence show that the proposed method tends to reduce the combinatorial complexity of the hybrid MPC problem to that of a one-step look-ahead optimization, greatly easing the online computation burden.
Supplemental materials: http://arxiv.org/abs/1910.08251
Under review (arXiv available). Comments welcome.
July 20, 2020. PhD Defense. Congratulations to Lucas Manuelli for successfully defending his PhD thesis!
May 29, 2020. PhD Defense. Congratulations to Shen Shen for successfully defending her thesis!
September 18, 2019. PhD Defense. Congratulations to Twan Koolen for successfully defending his thesis!
August 19, 2019. PhD Defense. Congratulations to Pete Florence for successfully defending his thesis!
October 15, 2018. PhD Defense. Congratulations to Robin Deits for successfully defending his thesis!
October 3, 2018. Award. Congratulations to Pete Florence and Lucas Manuelli whose paper Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation won the Conference Best Paper Award at CoRL 2018!
September 19, 2018. Award. Congratulations to Pete Florence and Lucas Manuelli whose paper Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation won the first ever Amazon Robotics Best Technical Paper Award (2018).
June 18, 2018. Award. Congratulations to Ani Majumdar whose paper Funnel libraries for real-time robust feedback motion planning won the first ever International Journal of Robotics Research Paper of the Year (2017).
April 26, 2018. Award. Congratulations to Katy Muhlrad for winning the "Audience Choice Award" at the SuperUROP Showcase for her work on "Using GelSight to Identify Objects by Touch".
July 26, 2017. Defense. Frank Permenter successfully defended his thesis, titled "Reduction methods in semidefinite and conic optimization". Congratulations Frank!
May 19, 2017. Award. Pete Florence was awarded the EECS Masterworks award. Congratulations Pete!
May 19, 2017. Award. Sarah Hensley was awarded the 2017 Best SuperUROP Presentation award. Congratulations Sarah!
May 16, 2017. PhD Defense. Michael Posa successfully defended his thesis, titled "Optimization for Control and Planning of Multi-Contact Dynamic Motion". Congratulations Michael!
May 15, 2017. Award. Our paper describing the planning and control that we implemented on Atlas for the DARPA Robotics Challenge was recognized with the IEEE-RAS Technical Commmittee on Whole-Body Control 2016 Best Paper of the Year award.
January 28, 2017. Video. Amara Mesnik put together a great mini-documentary on MIT's entry in the DARPA Robotics Challenge.
May 13, 2016. PhD Defense. Ani Majumdar has successfully defended his PhD thesis. Congratulations Ani! Click on the link to watch his talk, and check the publications page to read his thesis.
February 24, 2016. Media. NOVA's documentary on the DARPA Robotics Challenge, titled "Rise of the Robots" is online now.
December 7, 2015. PhD Defense. Andy Barry has successfully defended his PhD thesis. Congratulations Andy! Click on the link to watch his talk.
November 18, 2015. In the news. NASA's R5 humanoid robot is coming to MIT. We're very excited to have the opportunity to do research on this amazing platform.
For Group Members:|