Nathan D. Ratliff

Maximum margin planning

Imitation learning of sequential, goal-directed behavior by standard supervised techniques is often difficult. We frame learning such behaviors as a maximum margin structured prediction problem over a space of policies. In this approach, we learn mappings from features to cost so an optimal policy in an MDP with these cost mimics the experts behavior. Further, we demonstrate a simple, provably efficient approach to structured maximum margin learning, based on the subgradient method, that leverages existing fast algorithms for inference. Although the technique is general, it is particularly relevant in problems where A* and dynamic programming approaches make learning policies tractable in problems beyond the limitations of a QP formulation. We demonstrate our approach applied to route planning for outdoor mobile robots, where the behavior a designer wishes a planner to execute is often clear, while specifying cost functions that engender this behavior is a much more difficult task.

CHOMP: Gradient optimization techniques for efficient motion planning

Existing high-dimensional motion planning algorithms are simultaneously overpowered and underpowered. In domains sparsely populated by obstacles, the heuristics used by sampling-based planners to navigate “narrow passages” can be needlessly complex; furthermore, additional post-processing is required to remove the jerky or extraneous motions from the paths that such planners generate. In this paper, we present CHOMP, a novel method for continuous path refinement that uses covariant gradient techniques to improve the quality of sampled trajectories. Our optimization technique both optimizes higher-order dynamics and is able to converge over a wider range of input paths relative to previous path optimization strategies. In particular, we relax the collision-free feasibility prerequisite on input paths required by those strategies. As a result, CHOMP can be used as a standalone motion planner in many real-world planning queries. We demonstrate the effectiveness of our proposed method in manipulation planning for a 6-DOF robotic arm as well as in trajectory generation for a walking quadruped robot.

Planning-based prediction for pedestrians

We present a novel approach for determining robot movements that efficiently accomplish the robots tasks while not hindering the movements of people within the environment. Our approach models the goal-directed trajectories of pedestrians using maximum entropy inverse optimal control. The advantage of this modeling approach is the generality of its learned cost function to changes in the environment and to entirely different environments. We employ the predictions of this model of pedestrian trajectories in a novel incremental planner and quantitatively show the improvement in hindrance-sensitive robot trajectory planning provided by our approach.

Learning to search: Functional gradient techniques for imitation learning

Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time consuming, and ultimately expensive. The machine learning paradigm offers the promise of enabling “programming by demonstration” for developing high-performance robotic systems. Unfortunately, many “behavioral cloning” (Bain and Sammut in Machine intelligence agents. London: Oxford University Press, 1995; Pomerleau in Advances in neural information processing systems 1, 1989; LeCun et al. in Advances in neural information processing systems 18, 2006) approaches that utilize classical tools of supervised learning (e.g. decision trees, neural networks, or support vector machines) do not fit the needs of modern robotic systems. These systems are often built atop sophisticated planning algorithms that efficiently reason far into the future; consequently, ignoring these planning algorithms in lieu of a supervised learning approach often leads to myopic and poor-quality robot performance.While planning algorithms have shown success in many real-world applications ranging from legged locomotion (Chestnutt et al. in Proceedings of the IEEE-RAS international conference on humanoid robots, 2003) to outdoor unstructured navigation (Kelly et al. in Proceedings of the international symposium on experimental robotics (ISER), 2004; Stentz et al. in AUVSI’s unmanned systems, 2007), such algorithms rely on fully specified cost functions that map sensor readings and environment models to quantifiable costs. Such cost functions are usually manually designed and programmed. Recently, a set of techniques has been developed that explore learning these functions from expert human demonstration. These algorithms apply an inverse optimal control approach to find a cost function for which planned behavior mimics an expert’s demonstration.The work we present extends the Maximum Margin Planning (MMP) (Ratliff et al. in Twenty second international conference on machine learning (ICML06), 2006a) framework to admit learning of more powerful, non-linear cost functions. These algorithms, known collectively as LEARCH (LEArning to seaRCH), are simpler to implement than most existing methods, more efficient than previous attempts at non-linearization (Ratliff et al. in NIPS, 2006b), more naturally satisfy common constraints on the cost function, and better represent our prior beliefs about the function’s form. We derive and discuss the framework both mathematically and intuitively, and demonstrate practical real-world performance with three applied case-studies including legged locomotion, grasp planning, and autonomous outdoor unstructured navigation. The latter study includes hundreds of kilometers of autonomous traversal through complex natural environments. These case-studies address key challenges in applying the algorithm in practical settings that utilize state-of-the-art planners, and which may be constrained by efficiency requirements and imperfect expert demonstration.

BiSpace Planning: Concurrent Multi-Space Exploration

We present a planning algorithm called BiSpace that produces fast plans to complex high-dimensional problems by simultaneously exploring multiple spaces. We specifically focus on finding robust solutions to manipulation and grasp planning problems by using BiSpace’s special characteristics to explore the work and configuration spaces of the environment and robot. Furthermore, we present a number of techniques for constructing informed heuristics to intelligently search through these highdimensional spaces. In general, the BiSpace planner is applicable to any problem involving multiple search spaces.

Imitation learning for locomotion and manipulation

Decision making in robotics often involves computing an optimal action for a given state, where the space of actions under consideration can potentially be large and state dependent. Many of these decision making problems can be naturally formalized in the multiclass classification framework, where actions are regarded as labels for states. One powerful approach to multiclass classification relies on learning a function that scores each action; action selection is done by returning the action with maximum score. In this work, we focus on two imitation learning problems in particular that arise in robotics. The first problem is footstep prediction for quadruped locomotion, in which the system predicts next footstep locations greedily given the current four-foot configuration of the robot over a terrain height map. The second problem is grasp prediction, in which the system must predict good grasps of complex free-form objects given an approach direction for a robotic hand. We present experimental results of applying a recently developed functional gradient technique for optimizing a structured margin formulation of the corresponding large non-linear multiclass classification problems.

Optimization and learning for rough terrain legged locomotion

We present a novel approach to legged locomotion over rough terrain that is thoroughly rooted in optimization. This approach relies on a hierarchy of fast, anytime algorithms to plan a set of footholds, along with the dynamic body motions required to execute them. Components within the planning framework coordinate to exchange plans, cost-to-go estimates, and ‘certificates’ that ensure the output of an abstract high-level planner can be realized by lower layers of the hierarchy. The burden of careful engineering of cost functions to achieve desired performance is substantially mitigated by a simple inverse optimal control technique. Robustness is achieved by real-time re-planning of the full trajectory, augmented by reflexes and feedback control. We demonstrate the successful application of our approach in guiding the LittleDog quadruped robot over a variety of types of rough terrain. Other novel aspects of our past research efforts include a variety of pioneering inverse optimal control techniques as well as a system for planning using arbitrary pre-recorded robot behavior.

Manipulation planning with goal sets using constrained trajectory optimization

Goal sets are omnipresent in manipulation: picking up objects, placing them on counters or in bins, handing them off — all of these tasks encompass continuous sets of goals. This paper describes how to design optimal trajectories that exploit goal sets. We extend CHOMP (Covariant Hamiltonian Optimization for Motion Planning), a recent trajectory optimizer that has proven effective on high-dimensional problems, to handle trajectory-wide constraints, and relate the solution to the intuition of taking unconstrained steps and subsequently projecting them onto the constraints. We then show how this projection simplifies for goal sets (i.e. constraints that affect only the end-point). Finally, we present experiments on a personal robotics platform that show the importance of exploiting goal sets in trajectory optimization for day-to-day manipulation tasks.

Real-time natural language corrections for assistive robotic manipulators

We propose a generalizable natural language interface that allows users to provide corrective instructions to an assistive robotic manipulator in real-time. This work is motivated by the desire to improve collaboration between humans and robots in a home environment. Allowing human operators to modify properties of how their robotic counterpart achieves a goal on-the-fly increases the utility of the system by incorporating the strengths of the human partner (e.g. visual acuity and environmental knowledge). This work is applicable to users with and without disability. Our natural language interface is based on the distributed correspondence graph, a probabilistic graphical model that assigns semantic meaning to user utterances in the context of the robot’s environment and current behavior. We then use the desired corrections to alter the behavior of the robotic manipulator by treating the modifications as constraints on the motion generation (planning) paradigm. In this paper, we highlight four dimensions along which a user may wish to correct the behavior of his or her assistive manipulator. We develop our language model using data collected from Amazon Mechanical Turk to capture a comprehensive sample of terminology that people use to describe desired corrections. We then develop an end-to-end system using open-source speech-to-text software and a Kinova Robotics MICO robotic arm. To demonstrate the efficacy of our approach, we run a pilot study with users unfamiliar with robotic systems and analyze points of failure and future directions.