arXiv subjects

Gaurav S. Sukhatme

Publications and source records attributed to Gaurav S. Sukhatme.

107 records · Page 6Linked to original sources

arXiv2020

Automatic Differentiation and Continuous Sensitivity Analysis of Rigid Body Dynamics

A key ingredient to achieving intelligent behavior is physical understanding that equips robots with the ability to reason about the effects of their actions in a dynamic environment. Several methods have been proposed to learn dynamics models from data that inform model-based control algorithms. While such learning-based approaches can model locally observed behaviors, they fail to generalize to more complex dynamics and under long time horizons. In this work, we introduce a differentiable physics simulator for rigid body dynamics. Leveraging various techniques for differential equation integration and gradient calculation, we compare different methods for parameter estimation that allow us to infer the simulation parameters that are relevant to estimation and control of physical systems. In the context of trajectory optimization, we introduce a closed-loop model-predictive control algorithm that infers the simulation parameters through experience while achieving cost-minimizing performance.

cs.RO↗

arXiv2019

Resilience in multi-robot target tracking through reconfiguration

We address the problem of maintaining resource availability in a networked multi-robot system performing distributed target tracking. In our model, robots are equipped with sensing and computational resources enabling them to track a target's position using a Distributed Kalman Filter (DKF). We use the trace of each robot's sensor measurement noise covariance matrix as a measure of sensing quality. When a robot's sensing quality deteriorates, the system's communication graph is modified by adding edges such that the robot with deteriorating sensor quality may share information with other robots to improve the team's target tracking ability. This computation is performed centrally and is designed to work without a large change in the number of active communication links. We propose two mixed integer semi-definite programming formulations (an 'agent-centric' strategy and a 'team-centric' strategy) to achieve this goal. We implement both formulations and a greedy strategy in simulation and show that the team-centric strategy outperforms the agent-centric and greedy strategies.

cs.RO↗

arXiv2019

Resilience by Reconfiguration: Exploiting Heterogeneity in Robot Teams

We propose a method to maintain high resource in a networked heterogeneous multi-robot system to resource failures. In our model, resources such as and computation are available on robots. The robots engaged in a joint task using these pooled resources. In our model, a resource on a particular robot becomes unavailable e.g., a sensor ceases to function due to a failure), the system reconfigures so that the robot continues to have to this resource by communicating with other robots. Specifically, we consider the problem of selecting edges to be in the system's communication graph after a resource has occurred. We define a metric that allows us to characterize the quality of the resource distribution in the represented by the communication graph. Upon a resource becoming unavailable due to failure, we reconfigure network so that the resource distribution is brought as to the ideal resource distribution as possible without a big change in the communication cost. Our approach uses integer semi-definite programming to achieve this goal. We also provide a simulated annealing method to compute a formation that satisfies the inter-robot distances imposed by the topology, along with other constraints. Our method can compute a communication topology, spatial formation, and formation change motion planning in a few seconds. We validate our method in simulation and real-robot experiments with a team of seven quadrotors.

cs.RO↗

arXiv2019

Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors

Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remarkably well to multiple different physical quadrotors. Our policies are low-level, i.e., we map the rotorcrafts' state directly to the motor outputs. The trained control policies are very robust to external disturbances and can withstand harsh initial conditions such as throws. We show how different training methodologies (change of the cost function, modeling of noise, use of domain randomization) might affect flight performance. To the best of our knowledge, this is the first work that demonstrates that a simple neural network can learn a robust stabilizing low-level quadrotor controller (without the use of a stabilizing PD controller) that is shown to generalize to multiple quadrotors.

cs.RO↗

arXiv2019

Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills

Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion planning pipelines, where multiple objectives must be met and the high-level context be taken into consideration. Learning from demonstration (LfD) provides a promising way to learn these kind of complex manipulation skills even from non-technical users. However, it is challenging for existing LfD methods to efficiently learn skills that can generalize to task specifications that are not covered by demonstrations. In this paper, we introduce a state transition model (STM) that generates joint-space trajectories by imitating motions from expert behavior. Given a few demonstrations, we show in real robot experiments that the learned STM can quickly generalize to unseen tasks and synthesize motions having longer time horizons than the expert trajectories. Compared to conventional motion planners, our approach enables the robot to accomplish complex behaviors from high-level instructions without laborious hand-engineering of planning objectives, while being able to adapt to changing goals during the skill execution. In conjunction with a trajectory optimizer, our STM can construct a high-quality skeleton of a trajectory that can be further improved in smoothness and precision. In combination with a learned inverse dynamics model, we additionally present results where the STM is used as a high-level planner. A video of our experiments is available at https://youtu.be/85DX9Ojq-90

cs.RO↗

arXiv2018

Planning Safe Paths through Hazardous Environments

Autonomous underwater vehicles (AUVs) are robotic platforms that are commonly used to map the sea floor, for example for benthic surveys or for naval mine countermeasures (MCM) operations. AUVs create an acoustic image of the survey area, such that objects on the seabed can be identified and, in the case of MCM, mines can be found and disposed of. The common method for creating such seabed maps is to run a lawnmower survey, which is a standard method in coverage path planning. We are interested in exploring alternate techniques for surveying areas of interest, in order to reduce mission time or assess feasible actions, such as finding a safe path through a hazardous region. In this paper, we use Gaussian Process regression to build models of seabed complexity data, obtained through lawnmower surveys. We evaluate several commonly used kernels to assess their modeling performance, which includes modeling discontinuities in the data. Our results show that an additive Matérn kernel is most suitable for modeling seabed complexity data. On top of the GP model, we use adaptations of two standard path planning methods, A* and RRT*, to find safe paths for marine vessels through the modeled areas. We evaluate the planned paths and also run a vehicle dynamics simulator to assess potential performance by a marine vessel.

cs.RO↗

arXiv2018

Data-Driven Learning and Planning for Environmental Sampling

Robots such as autonomous underwater vehicles (AUVs) and autonomous surface vehicles (ASVs) have been used for sensing and monitoring aquatic environments such as oceans and lakes. Environmental sampling is a challenging task because the environmental attributes to be observed can vary both spatially and temporally, and the target environment is usually a large and continuous domain whereas the sampling data is typically sparse and limited. The challenges require that the sampling method must be informative and efficient enough to catch up with the environmental dynamics. In this paper we present a planning and learning method that enables a sampling robot to perform persistent monitoring tasks by learning and refining a dynamic "data map" that models a spatiotemporal environment attribute such as ocean salinity content. Our environmental sampling framework consists of two components: to maximize the information collected, we propose an informative planning component that efficiently generates sampling waypoints that contain the maximal information; To alleviate the computational bottleneck caused by large-scale data accumulated, we develop a component based on a sparse Gaussian Process whose hyperparameters are learned online by taking advantage of only a subset of data that provides the greatest contribution. We validate our method with both simulations running on real ocean data and field trials with an ASV in a lake environment. Our experiments show that the proposed framework is both accurate in learning the environmental data map and efficient in catching up with the dynamic environmental changes.

cs.RO↗

arXiv2018

A Solution to Time-Varying Markov Decision Processes

We consider a decision-making problem where the environment varies both in space and time. Such problems arise naturally when considering e.g., the navigation of an underwater robot amidst ocean currents or the navigation of an aerial vehicle in wind. To model such spatiotemporal variation, we extend the standard Markov Decision Process (MDP) to a new framework called the Time-Varying Markov Decision Process (TVMDP). The TVMDP has a time-varying state transition model and transforms the standard MDP that considers only immediate and static uncertainty descriptions of state transitions, to a framework that is able to adapt to future time-varying transition dynamics over some horizon. We show how to solve a TVMDP via a redesign of the MDP value propagation mechanisms by incorporating the introduced dynamics along the temporal dimension. We validate our framework in a marine robotics navigation setting using spatiotemporal ocean data and show that it outperforms prior efforts.

cs.RO↗

arXiv2017

Downwash-Aware Trajectory Planning for Large Quadrotor Teams

We describe a method for formation-change trajectory planning for large quadrotor teams in obstacle-rich environments. Our method decomposes the planning problem into two stages: a discrete planner operating on a graph representation of the workspace, and a continuous refinement that converts the non-smooth graph plan into a set of C^k-continuous trajectories, locally optimizing an integral-squared-derivative cost. We account for the downwash effect, allowing safe flight in dense formations. We demonstrate the computational efficiency in simulation with up to 200 robots and the physical plausibility with an experiment with 32 nano-quadrotors. Our approach can compute safe and smooth trajectories for hundreds of quadrotors in dense environments with obstacles in a few minutes.

cs.RO↗

arXiv2017

A Spatio-Temporal Representation for the Orienteering Problem with Time-Varying Profits

We consider an orienteering problem (OP) where an agent needs to visit a series (possibly a subset) of depots, from which the maximal accumulated profits are desired within given limited time budget. Different from most existing works where the profits are assumed to be static, in this work we investigate a variant that has arbitrary time-dependent profits. Specifically, the profits to be collected change over time and they follow different (e.g., independent) time-varying functions. The problem is of inherent nonlinearity and difficult to solve by existing methods. To tackle the challenge, we present a simple and effective framework that incorporates time-variations into the fundamental planning process. Specifically, we propose a deterministic spatio-temporal representation where both spatial description and temporal logic are unified into one routing topology. By employing existing basic sorting and searching algorithms, the routing solutions can be computed in an extremely efficient way. The proposed method is easy to implement and extensive numerical results show that our approach is time efficient and generates near-optimal solutions.

cs.AI↗

arXiv2016

Designing Sparse Reliable Pose-Graph SLAM: A Graph-Theoretic Approach

In this paper, we aim to design sparse D-optimal (determinantoptimal) pose-graph SLAM problems through the synthesis of sparse graphs with the maximum weighted number of spanning trees. Characterizing graphs with the maximum number of spanning trees is an open problem in general. To tackle this problem, several new theoretical results are established in this paper, including the monotone log-submodularity of the weighted number of spanning trees. By exploiting these structures, we design a complementary pair of near-optimal efficient approximation algorithms with provable guarantees. Our theoretical results are validated using random graphs and a publicly available pose-graph SLAM dataset.

cs.RO↗

arXiv2016

Informative Planning and Online Learning with Sparse Gaussian Processes

A big challenge in environmental monitoring is the spatiotemporal variation of the phenomena to be observed. To enable persistent sensing and estimation in such a setting, it is beneficial to have a time-varying underlying environmental model. Here we present a planning and learning method that enables an autonomous marine vehicle to perform persistent ocean monitoring tasks by learning and refining an environmental model. To alleviate the computational bottleneck caused by large-scale data accumulated, we propose a framework that iterates between a planning component aimed at collecting the most information-rich data, and a sparse Gaussian Process learning component where the environmental model and hyperparameters are learned online by taking advantage of only a subset of data that provides the greatest contribution. Our simulations with ground-truth ocean data shows that the proposed method is both accurate and efficient.

cs.RO↗

arXiv2016

Toward a Science of Autonomy for Physical Systems: Defense

Militaries around the world have long been cognizant of the potential benefits associated with autonomous systems both in the conduct of warfare and in its prevention. This has lead to the declaration by some that this technology will lead to a fundamental change in the ways in which war is conducted, i.e., a revolution in military affairs (RMA) not unlike gunpowder, the long bow, the rifled bullet, the aircraft carrier, etc. Indeed the United States has created roadmaps for robotics with ever-increasing autonomous capability that span almost 40 years. These systems span air, sea, sea surface, littoral, ground and subterranean environments. There are serious societal and ethical concerns associated with the deployment of this technology that remain unaddressed. How can sufficient protection be afforded noncombatants? What about civilian blowback, where this technology may end up being used in policing operations against domestic groups? How can we protect the fundamental human rights of all involved? Considerable discussion is being conducted at an international level, including at the United Nations Convention on Certain Conventional Weapons (CCW) over the past two years, debating if and how such systems, particularly lethal platforms should be banned or regulated.

cs.CY↗

arXiv2016

Learning Relevant Features for Manipulation Skills using Meta-Level Priors

Robots can generalize manipulation skills between different scenarios by adapting to the features of the objects being manipulated. Selecting the set of relevant features for generalizing skills has usually been performed manually by a human. Alternatively, a robot can learn to select relevant features autonomously. However, feature selection usually requires a large amount of training data, which would require many demonstrations. In order to learn the relevant features more efficiently, we propose using a meta-level prior to transfer the relevance of features from previously learned skills. The experiments show that the meta-level prior more than doubles the average precision and recall of the feature selection when compared to a standard uniform prior. The proposed approach was used to learn a variety of manipulation skills, including pushing, cutting, and pouring.

cs.RO↗

arXiv2016

Maximizing the Weighted Number of Spanning Trees: Near-$t$-Optimal Graphs

Designing well-connected graphs is a fundamental problem that frequently arises in various contexts across science and engineering. The weighted number of spanning trees, as a connectivity measure, emerges in numerous problems and plays a key role in, e.g., network reliability under random edge failure, estimation over networks and D-optimal experimental designs. This paper tackles the open problem of designing graphs with the maximum weighted number of spanning trees under various constraints. We reveal several new structures, such as the log-submodularity of the weighted number of spanning trees in connected graphs. We then exploit these structures and design a pair of efficient approximation algorithms with performance guarantees and near-optimality certificates. Our results can be readily applied to a wide verity of applications involving graph synthesis and graph sparsification scenarios.

cs.DS↗

arXiv2012

Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena

The problem of modeling and predicting spatiotemporal traffic phenomena over an urban road network is important to many traffic applications such as detecting and forecasting congestion hotspots. This paper presents a decentralized data fusion and active sensing (D2FAS) algorithm for mobile sensors to actively explore the road network to gather and assimilate the most informative data for predicting the traffic phenomenon. We analyze the time and communication complexity of D2FAS and demonstrate that it can scale well with a large number of observations and sensors. We provide a theoretical guarantee on its predictive performance to be equivalent to that of a sophisticated centralized sparse approximation for the Gaussian process (GP) model: The computation of such a sparse approximate GP model can thus be parallelized and distributed among the mobile sensors (in a Google-like MapReduce paradigm), thereby achieving efficient and scalable prediction. We also theoretically guarantee its active sensing performance that improves under various practical environmental conditions. Empirical evaluation on real-world urban road network data shows that our D2FAS algorithm is significantly more time-efficient and scalable than state-of-the-art centralized algorithms while achieving comparable predictive performance.

cs.LG↗

arXiv2011

Active Classification: Theory and Application to Underwater Inspection

We discuss the problem in which an autonomous vehicle must classify an object based on multiple views. We focus on the active classification setting, where the vehicle controls which views to select to best perform the classification. The problem is formulated as an extension to Bayesian active learning, and we show connections to recent theoretical guarantees in this area. We formally analyze the benefit of acting adaptively as new information becomes available. The analysis leads to a probabilistic algorithm for determining the best views to observe based on information theoretic costs. We validate our approach in two ways, both related to underwater inspection: 3D polyhedra recognition in synthetic depth maps and ship hull inspection with imaging sonar. These tasks encompass both the planning and recognition aspects of the active classification problem. The results demonstrate that actively planning for informative views can reduce the number of necessary views by up to 80% when compared to passive methods.

cs.RO↗