Author name cluster

Maya Cakmak

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

27 papers

2 author rows

IROS Conference 2024 Conference Paper

Diffusion-PbD: Generalizable Robot Programming by Demonstration with Diffusion Features

Michael Murray
Entong Su
Maya Cakmak

Programming by Demonstration (PbD) is an intuitive technique for programming robot manipulation skills by demonstrating the desired behavior. However, most existing approaches either require extensive demonstrations or fail to generalize beyond their initial demonstration conditions. We introduce Diffusion-PbD, a novel approach to PbD that enables users to synthesize generalizable robot manipulation skills from a single demonstration by utilizing the representations captured by pre-trained visual foundation models. At demonstration time, hand and object detection priors are used to extract waypoints from the human demonstrations anchored to reference points in the scene. At execution time, features from pre-trained diffusion models are leveraged to identify corresponding reference points in new observations. We validate this approach through a series of real-world robot experiments, showing that Diffusion-PbD is applicable to a wide range of manipulation tasks and has strong ability to generalize to unseen objects, camera viewpoints, and scenes. Code and supplementary videos can be found at https://diffusion-pbd.github.io

IROS Conference 2024 Conference Paper

Fast Explicit-Input Assistance for Teleoperation in Clutter

Nick Walker 0001
Xuning Yang
Animesh Garg
Maya Cakmak
Dieter Fox
Claudia Pérez-D'Arpino

The performance of prediction-based assistance for robot teleoperation degrades in unseen or goal-rich environments due to incorrect or quickly-changing intent inferences. Poor predictions can confuse operators or cause them to change their control input to implicitly signal their goal. We present a new assistance interface for robotic manipulation where an operator can explicitly communicate a manipulation goal by pointing the end-effector. The pointing target specifies a region for local pose generation and optimization, providing interactive control over grasp and placement pose candidates. We evaluate this explicit pointing interface against an implicit inference-based assistance scheme and an unassisted control condition in a within-subjects user study (N=20), where participants teleoperate a simulated robot to complete a multi-step singulation and stacking task in cluttered environments. We find that operators prefer the explicit interface, experience fewer pick failures and report lower cognitive workload. Our code is available at: github.com/NVlabs/fast-explicit-teleop.

ICRA Conference 2024 Conference Paper

Learning to Grasp in Clutter with Interactive Visual Failure Prediction

Michael Murray
Abhishek Gupta 0004
Maya Cakmak

Modern warehouses process millions of unique objects which are often stored in densely packed containers. To automate tasks in this environment, a robot must be able to pick diverse objects from highly cluttered scenes. Real-world learning is a promising approach, but executing picks in the real world is time-consuming, can induce costly failures, and often requires extensive human intervention, which causes operational burden and limits the scope of data collection and deployments. In this work, we leverage interactive probes to visually evaluate grasps in clutter without fully executing picks, a capability we refer to as Interactive Visual Failure Prediction (IVFP). This enables autonomous verification of grasps during execution to avoid costly downstream failures as well as autonomous reward assignment, providing supervision to continuously shape and improve grasping behavior as the robot gathers experience in the real world, without constantly requiring human intervention. Through experiments on a Stretch RE1 robot, we study the effect that IVFP has on performance - both in terms of effective data throughput and success rate, and show that this approach leads to grasping policies that outperform policies trained with human supervision alone, while requiring significantly less human intervention. Code, datasets, and videos available at https://robo-ivfp.github.io

ICRA Conference 2022 Conference Paper

HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers

Yu-Wei Chao
Chris Paxton 0001
Yu Xiang 0001
Wei Yang 0019
Balakumar Sundaralingam
Tao Chen 0046
Adithyavairavan Murali
Maya Cakmak

We introduce a new simulation benchmark “Han-doverSim” for human-to-robot object handovers. To simulate the giver's motion, we leverage a recent motion capture dataset of hand grasping of objects. We create training and evaluation environments for the receiver with standardized protocols and metrics. We analyze the performance of a set of baselines and show a correlation with a real-world evaluation. 1 1 Code is open sourced at https://handover-sim.github.io.

ICRA Conference 2022 Conference Paper

Model Predictive Control for Fluid Human-to-Robot Handovers

Wei Yang 0019
Balakumar Sundaralingam
Chris Paxton 0001
Iretiayo Akinola
Yu-Wei Chao
Maya Cakmak
Dieter Fox

Human-robot handover is a fundamental yet challenging task in human-robot interaction and collaboration. Recently, remarkable progressions have been made in human-to-robot handovers of unknown objects by using learning-based grasp generators. However, how to responsively generate smooth motions to take an object from a human is still an open question. Specifically, planning motions that take human comfort into account is not a part of the human-robot handover process in most prior works. In this paper, we propose to generate smooth motions via an efficient model-predictive control (MPC) framework that integrates perception and complex domain-specific constraints into the optimization problem. We introduce a learning-based grasp reachability model to select candidate grasps which maximize the robot's manipulability, giving it more freedom to satisfy these constraints. Finally, we integrate a neural net force/torque classifier that detects contact events from noisy data. We conducted human-to-robot handover experiments on a diverse set of objects with several users ( $N=4$ ) and performed a systematic evaluation of each module. The study shows that the users preferred our MPC approach over the baseline system by a large margin.

IROS Conference 2021 Conference Paper

Cursor-based Robot Tele-manipulation through 2D-to-SE2 Interfaces

Maria E. Cabrera
Kavi Dey
Kavita Krishnaswamy
Tapomayukh Bhattacharjee
Maya Cakmak

Cursor-based tele-operation interfaces for manipulators can enable widely available and accessible control of robots to make many near term applications possible. However, their efficiency is restricted by the challenge of controlling 6 Degrees-of-Freedom (DoF) with 2D input from the cursor. Existing interfaces make use of different strategies to tackle this challenge, including viewpoint constraints, mode switching, and visual overlays, but it is unclear how these strategies impact the efficiency and accessibility of the interface. In this paper we characterize the design space of cursor-based robot control interfaces and compare alternatives in two user studies. Study 1 (N=216) compares nine alternative interfaces focusing on control of 3 DoFs to understand the differences of the interfaces at the basic level and examine the impact of task parameters on efficiency. Study 2 (N=60) compares a subset of the interfaces integrated into a system that allows full control of a robot manipulator from three orthogonal views. We also present a framework for heuristically evaluating accessibility of these interfaces and discuss the efficiency and accessibility trade-off with recommendations.

ICRA Conference 2021 Conference Paper

Reactive Human-to-Robot Handovers of Arbitrary Objects

Wei Yang 0019
Chris Paxton 0001
Arsalan Mousavian
Yu-Wei Chao
Maya Cakmak
Dieter Fox

Human-robot object handovers have been an actively studied area of robotics over the past decade; however, very few techniques and systems have addressed the challenge of handing over diverse objects with arbitrary appearance, size, shape, and deformability. In this paper, we present a vision-based system that enables reactive human-to-robot handovers of unknown objects. Our approach combines closed-loop motion planning with real-time, temporally consistent grasp generation to ensure reactivity and motion smoothness. Our system is robust to different object positions and orientations, and can grasp both rigid and non-rigid objects. We demonstrate the generalizability, usability, and robustness of our approach on a novel benchmark set of 26 diverse household objects, a user study with six participants handing over a subset of 15 objects, and a systematic evaluation examining different ways of handing objects.

IROS Conference 2020 Conference Paper

Human Grasp Classification for Reactive Human-to-Robot Handovers

Wei Yang 0019
Chris Paxton 0001
Maya Cakmak
Dieter Fox

Transfer of objects between humans and robots is a critical capability for collaborative robots. Although there has been a recent surge of interest in human-robot handovers, most prior research focus on robot-to-human handovers. Further, work on the equally critical human-to-robot handovers often assumes humans can place the object in the robot’s gripper. In this paper, we propose an approach for human-to-robot handovers in which the robot meets the human halfway, by classifying the human’s grasp of the object and quickly planning a trajectory accordingly to take the object from the human’s hand according to their intent. To do this, we collect a human grasp dataset which covers typical ways of holding objects with various hand shapes and poses, and learn a deep model on this dataset to classify the hand grasps into one of these categories. We present a planning and execution approach that takes the object from the human hand according to the detected grasp and hand position, and replans as necessary when the handover is interrupted. Through a systematic evaluation, we demonstrate that our system results in more fluent handovers versus two baselines. We also present findings from a user study (N = 9) demonstrating the effectiveness and usability of our approach with naive users in different scenarios. More information can be found at http://wyang.me/handovers.

ICRA Conference 2019 Conference Paper

Robot Object Referencing through Legible Situated Projections

Thomas Weng
Leah Perlmutter
Stefanos Nikolaidis
Siddhartha S. Srinivasa
Maya Cakmak

The ability to reference objects in the environment is a key communication skill that robots need for complex, task-oriented human-robot collaborations. In this paper we explore the use of projections, which are a powerful communication channel for robot-to-human information transfer as they allow for situated, instantaneous, and parallelized visual referencing. We focus on the question of what makes a good projection for referencing a target object. To that end, we mathematically formulatelegibility of projections intended to reference an object, and propose alternative arrow-object match functions for optimally computing the placement of an arrow to indicate a target object in a cluttered scene. We implement our approach on a PR2 robot with a head-mounted projector. Through an online (48 participants) and an in-person (12 participants) user study we validate the effectiveness of our approach, identify the types of scenes where projections may fail, and characterize the differences between alternative match functions.

IROS Conference 2019 Conference Paper

Synthesizing Robot Manipulation Programs from a Single Observed Human Demonstration

Justin Huang
Dieter Fox
Maya Cakmak

Programming by Demonstration (PbD) lets users with little technical background program a wide variety of manipulation tasks for robots, but it should be as intuitive as possible for users while requiring as little time as possible. In this paper, we present a Programming by Demonstration system that synthesizes manipulation programs from a single observed demonstration, allowing users to program new tasks for a robot simply by performing the task once themselves. A human-in-the-loop interface helps users make corrections to the perceptual state as needed. We introduce Object Interaction Programs as a representation of multi-object, bimanual manipulation tasks and present algorithms for extracting programs from observed demonstrations and transferring programs to a robot to perform the task in a new scene. We demonstrate the expressivity and generalizability of our approach through an evaluation on a benchmark of complex tasks.

ICRA Conference 2018 Conference Paper

Robotic Cleaning Through Dirt Rearrangement Planning with Learned Transition Models

Sarah Elliott
Maya Cakmak

We address the problem of enabling a manipulator to move arbitrary amounts and configurations of dirt on a surface to a goal region using a cleaning tool. We represent this problem as heuristic search with a set of primitive dirt-oriented tool actions. We present dirt and action representations that allow efficient learning and prediction of future dirt states, given the current dirt state and applied action. We also present a method for sampling promising actions based on a clustering of dirt states and heuristics for planning. We demonstrate the effectiveness of our approach on challenging cleaning tasks through implementations on PR2 and Fetch robots.

IROS Conference 2018 Conference Paper

Simultaneous End-User Programming of Goals and Actions for Robotic Shelf Organization

Ying Siu Liang
Damien Pellier
Humbert Fiorino
Sylvie Pesty
Maya Cakmak

Arrangement of items on shelves in stores or warehouses is a tedious, repetitive task that can be feasible for robots to perform. The diversity of products that are available in stores and the different setups and preferences of each store makes pre-programming a robot for this task extremely challenging. Instead, our work argues for enabling end-users to customize the robot to their specific objects and setup at deployment time by programming it themselves. To that end, this paper contributes (i) a task representation for shelf arrangements based on a large dataset of grocery store shelf images, (ii) a method for inferring goal configurations from user inputs including demonstrations and direct parameter specifications, and (iii) a system implementation of the proposed approach that allows simultaneously learning task goals and actions. We evaluate our goal inference approach with ten different teaching strategies that combine alternative user inputs in different ways on the large dataset of grocery configurations, as well as with real human teachers through an online user study (N=32). We evaluate our full system implemented on a Fetch mobile manipulator on eight benchmark tasks that demonstrate end-to-end programming and execution of shelf arrangement tasks.

IROS Conference 2017 Conference Paper

Flexible user specification of perceptual landmarks for robot manipulation

Justin Huang
Maya Cakmak

Programming robots to do manipulation tasks requires users to specify relevant perceptual landmarks, which include objects, parts of objects, or parts of the workspace. While many techniques have been developed for object detection, few are designed to detect arbitrary parts of objects or of the workspace. This paper presents CustomLandmarks, a flexible tool that lets non-roboticists build their own perceptual detectors for many kinds of landmarks. The system components include a simple 3D interface for specifying landmarks, a novel representation for landmarks, and an algorithm for locating landmarks in new scenes. We evaluate the system's detection performance through systematic experiments and by using the system to aid a PR2 robot with several manipulation tasks. Finally, we present a user study showing that novices to the system are able to understand and use CustomLandmarks quickly, creatively, and effectively.

IROS Conference 2017 Conference Paper

Interactive scene segmentation for efficient human-in-the-loop robot manipulation

Daniel J. Butler
Sarah Elliott
Maya Cakmak

While there has been tremendous progress in autonomous robot manipulation, environments with clutter and unknown objects remain challenging particularly for the perception algorithms that support manipulation. This paper adopts a human-aided perception paradigm and investigates alternative interactive segmentation methods to allow users to segment a target object or object part. Through a first user study (N=24) we compare four interactive segmentation methods and characterize the tradeoff between efficiency and accuracy. Next we develop a hybrid segmentation interface and integrate it into an end-to-end human-in-the-loop manipulation system. In a second user study (N=12) we compare the performance of this system to a direct gripper-control system that allows similar manipulation tasks to be performed in challenging scenes. We find that this system enables more efficient manipulation with a lower mental load on the user, while offering a similar task success rate.

IROS Conference 2016 Conference Paper

Autonomous question answering with mobile robots in human-populated environments

Michael Jae-Yoon Chung
Andrzej Pronobis
Maya Cakmak
Dieter Fox
Rajesh P. N. Rao

Autonomous mobile robots will soon become ubiquitous in human-populated environments. Besides their typical applications in fetching, delivery, or escorting, such robots present the opportunity to assist human users in their daily tasks by gathering and reporting up-to-date knowledge about the environment. In this paper, we explore this use case and present an end-to-end framework that enables a mobile robot to answer natural language questions about the state of a large-scale, dynamic environment asked by the inhabitants of that environment. The system parses the question and estimates an initial viewpoint that is likely to contain information for answering the question based on prior environment knowledge. Then, it autonomously navigates towards the viewpoint while dynamically adapting to changes and new information. The output of the system is an image of the most relevant part of the environment that allows the user to obtain an answer to their question. We additionally demonstrate the benefits of a continuously operating information gathering robot by showing how the system can answer retrospective questions about the past state of the world using incidentally recorded sensory data. We evaluate our approach with a custom mobile robot deployed in a university building, with questions collected from occupants of the building. We demonstrate our system's ability to respond to these questions in different environmental conditions.

ICRA Conference 2016 Conference Paper

Making objects graspable in confined environments through push and pull manipulation with a tool

Sarah Elliott
Michelle Valente
Maya Cakmak

Grasping objects in confined environments, such as shelves, fridges, or drawers, is challenging due to the difficulty of avoiding gripper and arm collisions with the surfaces surrounding the object. In this paper we explore the use of a tool to reconfigure objects in such environments so as to make them graspable. The proposed tool has a simple form that allows it to be used in confined environments and a high friction tool tip that enables not only pushing objects but also pulling them. Our approach involves learning predictive models of pre-defined object-directed tool actions from experience. For each action, we train a multi-modal regressor that maps the initial state of an object to changes in that state, such that future states of the object can be estimated. These allow the robot to choose a sequence of tool actions that yield graspable configurations. We demonstrate that our approach enables a PR2 robot to grasp five different objects from different, initially ungraspable, configurations on a shelf.

IROS Conference 2015 Conference Paper

Designing information gathering robots for human-populated environments

Michael Jae-Yoon Chung
Andrzej Pronobis
Maya Cakmak
Dieter Fox
Rajesh P. N. Rao

Advances in mobile robotics have enabled robots that can autonomously operate in human-populated environments. Although primary tasks for such robots might be fetching, delivery, or escorting, they present an untapped potential as information gathering agents that can answer questions for the community of co-inhabitants. In this paper, we seek to better understand requirements for such information gathering robots (InfoBots) from the perspective of the user requesting the information. We present findings from two studies: (i) a user survey conducted in two office buildings and (ii) a 4-day long deployment in one of the buildings, during which inhabitants of the building could ask questions to an InfoBot through a web-based interface. These studies allow us to characterize the types of information that InfoBots can provide for their users.

ICRA Conference 2015 Conference Paper

RoboFlow: A flow-based visual programming language for mobile manipulation tasks

Sonya Alexandrova
Zachary Tatlock
Maya Cakmak

General-purpose robots can perform a range of useful tasks in human environments; however, programming them to robustly function in all possible environments that they might encounter is unfeasible. Instead, our research aims to develop robots that can be programmed by its end-users in their context of use, so that the robot needs to robustly function in only one particular environment. This requires intuitive ways in which end-users can program their robot. To that end, this paper contributes a flow-based visual programming language, called RoboFlow, that allows programming of generalizable mobile manipulation tasks. RoboFlow is designed to (i) ensure a robust low-level implementation of program procedures on a mobile manipulator, and (ii) restrict the high-level programming as much as possible to avoid user errors while enabling expressive programs that involve branching, looping, and nesting. We present an implementation of RoboFlow on a PR2 mobile manipulator and demonstrate the generalizability and error handling properties of RoboFlow programs on everyday mobile manipulation tasks in human environments.

ICRA Conference 2015 Conference Paper

Robot Programming by Demonstration with situated spatial language understanding

Maxwell Forbes
Rajesh P. N. Rao
Luke Zettlemoyer
Maya Cakmak

Robot Programming by Demonstration (PbD) allows users to program a robot by demonstrating the desired behavior. Providing these demonstrations typically involves moving the robot through a sequence of states, often by physically manipulating it. This requires users to be co-located with the robot and have the physical ability to manipulate it. In this paper, we present a natural language based interface for PbD that removes these requirements and enables hands-free programming. We focus on programming object manipulation actions—our key insight is that such actions can be decomposed into known types of manipulator movements that are naturally described using spatial language; e. g. , object reference expressions and prepositions. Our method takes a natural language command and the current world state to infer the intended movement command and its parametrization. We implement this method on a two-armed mobile manipulator and demonstrate the different types of manipulation actions that can be programmed with it. We compare it to a kinesthetic PbD interface and we demonstrate our method's ability to deal with incomplete language.

ICRA Conference 2014 Conference Paper

Accelerating imitation learning through crowdsourcing

Michael Jae-Yoon Chung
Maxwell Forbes
Maya Cakmak
Rajesh P. N. Rao

Although imitation learning is a powerful technique for robot learning and knowledge acquisition from näıve human users, it often suffers from the need for expensive human demonstrations. In some cases the robot has an insufficient number of useful demonstrations, while in others its learning ability is limited by the number of users it directly interacts with. We propose an approach that overcomes these shortcomings by using crowdsourcing to collect a wider variety of examples from a large pool of human demonstrators online. We present a new goal-based imitation learning framework which utilizes crowdsourcing as a major source of human demonstration data. We demonstrate the effectiveness of our approach experimentally on a scenario where the robot learns to build 2D object models on a table from basic building blocks using knowledge gained from locals and online crowd workers. In addition, we show how the robot can use this knowledge to support human-robot collaboration tasks such as goal inference through object-part classification and missing-part prediction. We report results from a user study involving fourteen local demonstrators and hundreds of crowd workers on 16 different model building tasks.

AIJ Journal 2014 Journal Article

Eliciting good teaching from humans for machine learners

Maya Cakmak
Andrea L. Thomaz

We propose using computational teaching algorithms to improve human teaching for machine learners. We investigate example sequences produced naturally by human teachers and find that humans often do not spontaneously generate optimal teaching sequences for arbitrary machine learners. To elicit better teaching, we propose giving humans teaching guidance, which are instructions on how to teach, derived from computational teaching algorithms or heuristics. We present experimental results demonstrating that teaching guidance substantially improves human teaching in three different problem domains. This provides promising evidence that human intelligence and flexibility can be leveraged to achieve better sample efficiency when input data to a learning system comes from a human teacher.

IROS Conference 2014 Conference Paper

Enhanced robotic cleaning with a low-cost tool attachment

Zhe Xu
Maya Cakmak

Robots that can reliably manipulate human tools can do a diverse range of useful tasks in human environments. However, these tools are often difficult to manipulate, particularly given force requirements for applying the tool. This is often due to the mismatch between the robot's gripper and the tool handle designed for human hands. In this paper, we present the design of a low-cost universal tool attachment that makes the tool gripper-friendly. We demonstrate the performance gain provided by the attachment on 10 different tools in the three stages of tool use: grasping the tool, applying the tool, and placing the tool. Our experiments demonstrate that the attachment performs significantly better in all three stages of tool use.

AAAI Conference 2012 Conference Paper

Algorithmic and Human Teaching of Sequential Decision Tasks

Maya Cakmak
Manuel Lopes

A helpful teacher can significantly improve the learning rate of a learning agent. Teaching algorithms have been formally studied within the field of Algorithmic Teaching. These give important insights into how a teacher can select the most informative examples while teaching a new concept. However the field has so far focused purely on classification tasks. In this paper we introduce a novel method for optimally teaching sequential decision tasks. We present an algorithm that automatically selects the set of most informative demonstrations and evaluate it on several navigation tasks. Next, we explore the idea of using this algorithm to produce instructions for humans on how to choose examples when teaching sequential decision tasks. We present a user study that demonstrates the utility of such instructions.

IROS Conference 2011 Conference Paper

Human preferences for robot-human hand-over configurations

Maya Cakmak
Siddhartha S. Srinivasa
Min Kyung Lee
Jodi Forlizzi
Sara B. Kiesler

Handing over objects to humans is an essential capability for assistive robots. While there are infinite ways to hand an object, robots should be able to choose the one that is best for the human. In this paper we focus on choosing the robot and object configuration at which the transfer of the object occurs, i. e. the hand-over configuration. We advocate the incorporation of user preferences in choosing hand-over configurations. We present a user study in which we collect data on human preferences and a human-robot interaction experiment in which we compare hand-over configurations learned from human examples against configurations planned using a kinematic model of the human. We find that the learned configurations are preferred in terms of several criteria, however planned configurations provide better reachability. Additionally, we find that humans prefer hand-overs with default orientations of objects and we identify several latent variables about the robot's arm that capture significant human preferences. These findings point towards planners that can generate not only optimal but also preferable hand-over configurations for novel objects.

ICRA Conference 2008 Conference Paper

Using learned affordances for robotic behavior development

Mehmet Remzi Dogar
Emre Ugur
Erol Sahin
Maya Cakmak

"Developmental robotics" proposes that, instead of trying to build a robot that shows intelligence once and for all, what one must do is to build robots that can develop. These robots should be equipped with behaviors that are simple but enough to bootstrap the system. Then, as the robot interacts with its environment, it should display increasingly complex behaviors. In this paper, we propose such a development scheme for a mobile robot. J. J. Gibson's concept of "affordances" and a formalization of this concept provides the basis of this development scheme. We show that an autonomous robot can start with pre-coded primitive behaviors, and as it executes its behaviors randomly in an environment, it can learn the affordance relations between the environment and its behaviors. We then present two ways of using these learned structures, in achieving more complex, intentional behaviors. In the first case, the sequencing of these primitive behaviors are such that new more complex behaviors emerge. In the second case, the robot makes a "blending" of its pre-coded primitive behaviors to create new behaviors.

IROS Conference 2007 Conference Paper

From primitive behaviors to goal-directed behavior using affordances

Mehmet Remzi Dogar
Maya Cakmak
Emre Ugur
Erol Sahin

In this paper, we studied how a mobile robot equipped with a 3D laser scanner can start from primitive behaviors and learn to use them to achieve goal-directed behaviors. For this purpose, we propose a learning scheme that is based on the concept of "affordances", where the robot first learns about the different kind of effects it can create in the environment and then links these effects with the perception of the initial environment and the executed primitive behavior. It uses these learned relations to create certain effects in the environment and achieve more complex behaviors.

ICRA Conference 2007 Conference Paper

The learning and use of traversability affordance using range images on a mobile robot

Emre Ugur
Mehmet Remzi Dogar
Maya Cakmak
Erol Sahin

We are interested in how the concept of affordances can affect our view to autonomous robot control, and how the results obtained from autonomous robotics can be reflected back upon the discussion and studies on the concept of affordances. In this paper, we studied how a mobile robot, equipped with a 3D laser scanner, can learn to perceive the traversability affordance and use it to wander in a room tilled with spheres, cylinders and boxes. The results showed that after learning, the robot can wander around avoiding contact with non-traversable objects (i. e. boxes, upright cylinders, or lying cylinders in certain orientation), but moving over traversable objects (such as spheres, and lying cylinders in a rollable orientation with respect to the robot) rolling them out of its way. We have shown that for each action approximately 1% of the perceptual features were relevant to determine whether it is afforded or not and that these relevant features are positioned in certain regions of the range image. The experiments are conducted both using a physics-based simulator and on a real robot.