Search for: All records

State estimation and control are often addressed separately, leading to unsafe execution due to sensing noise, execution errors, and discrepancies between the planning model and reality. Simultaneous control and trajectory estimation using probabilistic graphical models has been proposed as a unified solution to these challenges. Previous work, however, relies heavily on appropriate Gaussian priors and is limited to holonomic robots with linear time-varying models. The current research extends graphical optimization methods to vehicles with arbitrary dynamical models via Simultaneous Trajectory Estimation and Local Adaptation (STELA). The overall approach initializes feasible trajectories using a kinodynamic, sampling-based motion planner. Then, it simultaneously: (i) estimates the past trajectory based on noisy observations, and (ii) adapts the controls to be executed to minimize deviations from the planned, feasible trajectory, while avoiding collisions. The proposed factor graph representation of trajectories in STELA can be applied for any dynamical system given access to first or second-order state update equations, and introduces the duration of execution between two states in the trajectory discretization as an optimization variable. These features provide both generalization and flexibility in trajectory following. In addition to targeting computational efficiency, the proposed strategy performs incremental updates of the factor graph using the iSAM algorithm and introduces a time-window mechanism. This mechanism allows the factor graph to be dynamically updated to operate over a limited history and forward horizon of the planned trajectory. This enables online updates of controls at a minimum of 10Hz. Experiments demonstrate that STELA achieves at least comparable performance to previous frameworks on idealized vehicles with linear dynamics. STELA also directly applies to and successfully solves trajectory following problems for more complex dynamical models. Beyond generalization, simulations assess STELA's robustness under varying levels of sensing and execution noise, while ablation studies highlight the importance of different components of STELA. Real-world experiments validate STELA's practical applicability on a low-cost MuSHR robot, which exhibits high noise and non-trivial dynamics. 

Object insertion under tight tolerances (less than 1mm) is an important but challenging assembly task as even small errors can result in undesirable contacts. Recent efforts focused on Reinforcement Learning (RL), which often depends on careful definition of dense reward functions. This work proposes an effective strategy for such tasks that integrates traditional model-based control with RL to achieve improved insertion accuracy. The policy is trained exclusively in simulation and is zero-shot transferred to the real system. It employs a potential field-based controller to acquire a model-based policy for inserting a plug into a socket given full observability in simulation. This policy is then integrated with residual RL, which is trained in simulation given only a sparse, goal-reaching reward. A curriculum scheme over observation noise and action magnitude is used for training the residual RL policy. Both policy components use as input the SE(3) poses of both the plug and the socket and return the plug's SE(3) pose transform, which is executed by a robotic arm using a controller. The integrated policy is deployed on the real system without further training or fine-tuning, given a visual SE(3) object tracker. The proposed solution and alternatives are evaluated across a variety of objects and conditions in simulation and reality. The proposed approach outperforms recent RL-based methods in this domain and prior efforts with hybrid policies. Ablations highlight the impact of each component of the approach. 

Object insertion under tight tolerances (less than 1mm) is an important but challenging assembly task as even small errors can result in undesirable contacts. Recent efforts focused on Reinforcement Learning (RL), which often depends on careful definition of dense reward functions. This work proposes an effective strategy for such tasks that integrates traditional model-based control with RL to achieve improved insertion accuracy. The policy is trained exclusively in simulation and is zero-shot transferred to the real system. It employs a potential field-based controller to acquire a model-based policy for inserting a plug into a socket given full observability in simulation. This policy is then integrated with residual RL, which is trained in simulation given only a sparse, goal-reaching reward. A curriculum scheme over observation noise and action magnitude is used for training the residual RL policy. Both policy components use as input the SE(3) poses of both the plug and the socket and return the plug's SE(3) pose transform, which is executed by a robotic arm using a controller. The integrated policy is deployed on the real system without further training or fine-tuning, given a visual SE(3) object tracker. The proposed solution and alternatives are evaluated across a variety of objects and conditions in simulation and reality. The proposed approach outperforms recent RL-based methods in this domain and prior efforts with hybrid policies. Ablations highlight the impact of each component of the approach. 

This paper aims to improve the computational efficiency of motion planning for mobile robots with non-trivial dynamics through the use of learned controllers. Offline, a system-specific controller is first trained in an empty environment. Then, for the target environment, the approach constructs a data structure, a “Roadmap with Gaps,” to approximately learn how to solve planning queries using the learned controller. The roadmap nodes correspond to local regions. Edges correspond to applications of the learned controller that approximately connect these regions. Gaps arise as the controller does not perfectly connect pairs of individual states along edges. Online, given a query, a tree sampling-based motion planner uses the roadmap so that the tree’s expansion is informed towards the goal region. The tree expansion selects local subgoals given a wavefront on the roadmap that guides towards the goal. When the controller cannot reach a subgoal region, the planner resorts to random exploration to maintain probabilistic completeness and asymptotic optimality. The accompanying experimental evaluation shows that the approach significantly improves the computational efficiency of motion planning on various benchmarks, including physics-based vehicular models on uneven and varying friction terrains as well as a quadrotor under air pressure effects. 

Estimating the region of attraction (RoA) for a robot controller is essential for safe application and controller composition. Many existing methods require a closed-form expression that limit applicability to data-driven controllers. Methods that operate only over trajectory rollouts tend to be data-hungry. In prior work, we have demonstrated that topological tools based on Morse Graphs (directed acyclic graphs that combinatorially represent the underlying nonlinear dynamics) offer data-efficient RoA estimation without needing an analytical model. They struggle, however, with high-dimensional systems as they operate over a state-space discretization. This paper presents Morse Graph-aided discovery of Regions of Attraction in a learned Latent Space (MORALS) . The approach combines auto-encoding neural networks with Morse Graphs. MORALS shows promising predictive capabilities in estimating attractors and their RoAs for data-driven controllers operating over high-dimensional systems, including a 67-dim humanoid robot and a 96-dim 3-fingered manipulator. It first projects the dynamics of the controlled system into a learned latent space. Then, it constructs a reduced form of Morse Graphs representing the bistability of the underlying dynamics, i.e., detecting when the controller results in a desired versus an undesired behavior. The evaluation on high-dimensional robotic datasets indicates data efficiency in RoA estimation. 

The demographic representation of scientists featured in biology curricular materials do not match that of the undergraduate biology student population or of the U.S. population. In this lesson, we promote awareness of inequity in science through an exercise that encourages students to think about who is depicted as scientists in science curricular materials – specifically, biology textbooks. After a brief lecture on the scientific method, students read an excerpt from the introduction of a peer-reviewed publication that provides background information on the importance of representation in science. Next, students collect data from their own biology textbook about the representation of scientists who possess different identities and make a table depicting their results. Then, students fill in predictive graphs about demographic representation over time with respect to scientist identities including gender and race/ethnicity. Students compare their predictions with the results from the peer-reviewed article and discuss the implications of the results. Finally, students apply their new knowledge by designing an experiment that would examine representation of an alternative scientist identity, such as age. Students conclude by answering questions that gauge their knowledge of the scientific method. This activity uses a peer-reviewed publication as well as authentic data generated by the student to increase ideological awareness and teach societal influences on the process of science. 

Abstract Recent discoveries of water-rich Neptune-like exoplanets require a more detailed understanding of the phase diagram of H 2 O at pressure–temperature conditions relevant to their planetary interiors. The unusual non-dipolar magnetic fields of ice giant planets, produced by convecting liquid ionic water, are influenced by exotic high-pressure states of H 2 O—yet the structure of ice in this state is challenging to determine experimentally. Here we present X-ray diffraction evidence of a body-centered cubic (BCC) structured H 2 O ice at 200 GPa and ~ 5000 K, deemed ice XIX, using the X-ray Free Electron Laser of the Linac Coherent Light Source to probe the structure of the oxygen sub-lattice during dynamic compression. Although several cubic or orthorhombic structures have been predicted to be the stable structure at these conditions, we show this BCC ice phase is stable to multi-Mbar pressures and temperatures near the melt boundary. This suggests variable and increased electrical conductivity to greater depths in ice giant planets that may promote the generation of multipolar magnetic fields. 

Accelerator based neutrino oscillation experiments seek to measure the relative number of electron and muon (anti)neutrinos at different $L/E$values. However high statistics studies of neutrino interactions are almost exclusively measured using muon (anti)neutrinos since the dominant flavor of neutrinos produced by accelerator based beams are of the muon type. This work reports new measurements of electron (anti)neutrinos interactions in hydrocarbon, obtained by strongly suppressing backgrounds initiated by muon flavor (anti)neutrinos. Double differential cross sections as a function of visible energy transfer, $E_{\text{avail}}$, and transverse momentum transfer, $p_T$, or three momentum transfer, $q_3$are presented. Published by the American Physical Society2024 

Neutron production in antineutrino interactions can lead to bias in energy reconstruction in neutrino oscillation experiments, but these interactions have rarely been studied. MINERvA previously studied neutron production at an average antineutrino energy of ∼3 GeV in 2016 and found deficiencies in leading models. In this paper, the MINERvA 6 GeV average antineutrino energy dataset is shown to have similar disagreements. A measurement of the cross section for an antineutrino to produce two or more neutrons and have low visible energy is presented as an experiment-independent way to explore neutron production modeling. This cross section disagrees with several leading models’ predictions. Neutron modeling techniques from nuclear physics are used to quantify neutron detection uncertainties on this result. 

We present measurements of the cross section for antineutrino charged-current quasielasticlike scattering on hydrocarbon using the medium energy NuMI wide-band neutrino beam peaking at antineutrino energy hE¯νi ∼ 6 GeV. The measurements are presented as a function of the longitudinal momentum (pjj) and transverse momentum (pT) of the final state muon. This work complements our previously reported high statistics measurement in the neutrino channel and extends the previous antineutrino measurement made in a low energy beam at hE¯νi ∼ 3.5 GeV out to pT of 2.5 GeV=c. Current theoretical models do not completely describe the data in this previously unexplored high pT region. The single differential cross section as a function of four-momentum transfer (Q2 QE) now extends to 4 GeV2 with high statistics. The cross section as a function of Q2 QE shows that the tuned simulations developed by the MINERvA Collaboration that agreed well with the low energy beam measurements do not agree as well with the medium energy beam measurements. Newer neutrino interaction models such as the GENIE v3 tunes are better able to simulate the high Q2 QE region.